© 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. 33-TRANSCODER-HP
    7. 54041
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exus
    -0.28
    ials
    -0.26
    èĶļ
    -0.25
    aley
    -0.24
    _datas
    -0.24
    å¾®è§Ĥ
    -0.24
    matchCondition
    -0.24
    atics
    -0.24
    ography
    -0.24
    æ½®
    -0.24
    POSITIVE LOGITS
    illas
    0.33
    ç¥ł
    0.31
     ripe
    0.28
    asil
    0.28
    lime
    0.27
    èĤĿ
    0.27
     liver
    0.26
    ithe
    0.25
    -category
    0.25
     throat
    0.24
    Activations Density 0.013%

    No Known Activations