© 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. 109074
    Prev
    Next
    INDEX
    Explanations

    esophagus

    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
     vertically
    -0.30
    è§Ī
    -0.28
    æĬĹçĻĮ
    -0.27
    åŀĤ缴
    -0.26
    çݯçIJĥ
    -0.26
    kke
    -0.25
     dess
    -0.24
    _UNUSED
    -0.24
    (md
    -0.23
    ccion
    -0.23
    POSITIVE LOGITS
     Interval
    0.28
    stars
    0.27
    æľŁçĽ¼
    0.26
    éŁ¿
    0.26
    SDK
    0.25
     Round
    0.25
    lications
    0.25
    walk
    0.25
    den
    0.24
    .au
    0.24
    Activations Density 1.017%

    No Known Activations