© 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. 31-TRANSCODER-HP
    7. 19117
    Prev
    Next
    INDEX
    Explanations

    academic research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     personality
    -0.31
    æĢ§æł¼
    -0.30
    ivative
    -0.30
     affinity
    -0.29
    å¼¼
    -0.28
     Personality
    -0.27
    agram
    -0.27
     personalities
    -0.27
    ilib
    -0.26
    ivitÃł
    -0.25
    POSITIVE LOGITS
    æ´ŀ
    0.30
    广éĺĶ
    0.29
    åİĨåı²
    0.28
     dossier
    0.26
    .special
    0.26
    CCR
    0.25
    _BACKGROUND
    0.24
     funcs
    0.23
     photoc
    0.23
    åİĨåı²æĸĩåĮĸ
    0.23
    Activations Density 7.820%

    No Known Activations