© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107997
    Prev
    Next
    INDEX
    Explanations

    technical/specialized language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ĺ
    -0.30
     '::
    -0.28
     stepping
    -0.26
     =================================================================
    -0.26
     barrel
    -0.25
    åIJĦæľī
    -0.25
     tamp
    -0.25
     tracked
    -0.24
     yet
    -0.24
    pane
    -0.24
    POSITIVE LOGITS
    ï¬Ħ
    0.30
    cern
    0.28
    æݧ
    0.26
     awareness
    0.24
    entric
    0.24
    ROID
    0.24
    -aware
    0.24
    ogle
    0.24
    VEN
    0.23
    ,lat
    0.23
    Activations Density 0.468%

    No Known Activations