© 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. 57029
    Prev
    Next
    INDEX
    Explanations

    Code file headers

    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
    ç¼Ĩ
    -0.29
    rgan
    -0.28
    _overflow
    -0.26
     blackmail
    -0.25
    fans
    -0.25
    çĤ®
    -0.24
     morality
    -0.24
    brace
    -0.24
    pollo
    -0.24
    ä½łåĸľæ¬¢
    -0.23
    POSITIVE LOGITS
    大å¸Ī
    0.27
    ValuePair
    0.26
    åĬłè½½
    0.26
    鹧
    0.25
    èµł
    0.24
    azzo
    0.24
    ish
    0.24
    ç»ĵæŀĦæĢ§
    0.23
    ishes
    0.23
    è·³
    0.23
    Activations Density 0.001%

    No Known Activations