© 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. 8850
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     close
    -0.26
     da
    -0.26
    hash
    -0.25
    æĬĢæľ¯æĶ¯æĮģ
    -0.25
    .Metro
    -0.25
    close
    -0.24
     Close
    -0.24
    ä¸ĩ家
    -0.24
     hashlib
    -0.24
    HEMA
    -0.24
    POSITIVE LOGITS
     bli
    0.27
    ATTER
    0.27
     nargin
    0.25
    æĥħåĨµæĿ¥çľĭ
    0.25
    é¹ĥ
    0.25
     pl
    0.25
    bows
    0.25
    ropic
    0.24
    lags
    0.24
    	die
    0.24
    Activations Density 0.001%

    No Known Activations