© 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. 27-TRANSCODER-HP
    7. 8211
    Prev
    Next
    INDEX
    Explanations

    "N" names/identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     significance
    -0.28
    peer
    -0.28
     compos
    -0.27
    ény
    -0.26
    /nginx
    -0.26
     priorities
    -0.25
     Covent
    -0.25
     bonded
    -0.25
    gings
    -0.24
    below
    -0.24
    POSITIVE LOGITS
    icide
    0.33
    éĢ¢
    0.28
    -basket
    0.27
    onte
    0.27
    esti
    0.26
    kses
    0.26
    моÑĤ
    0.26
    quire
    0.26
    èĭĹ
    0.25
    沸
    0.25
    Activations Density 0.105%

    No Known Activations