© 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. 35-TRANSCODER-HP
    7. 40319
    Prev
    Next
    INDEX
    Explanations

    ack

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¼İ
    -0.26
    åı²ä¸ĬæľĢ
    -0.26
    .img
    -0.25
     MED
    -0.24
    æ¡Ĥ
    -0.24
    _FRE
    -0.24
    .hm
    -0.24
    Syn
    -0.24
    SE
    -0.23
     ME
    -0.23
    POSITIVE LOGITS
    ack
    0.61
    ACK
    0.54
    acks
    0.49
     ack
    0.49
    Ack
    0.48
     Ack
    0.45
    _ack
    0.39
     ACK
    0.39
     admission
    0.38
     admit
    0.37
    Activations Density 1.173%

    No Known Activations