© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41191
    Prev
    Next
    INDEX
    Explanations

    potre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goes
    -0.45
    go
    -0.45
     go
    -0.41
    .go
    -0.40
     went
    -0.39
    went
    -0.36
     Went
    -0.36
     gone
    -0.35
     going
    -0.35
    åİ»
    -0.35
    POSITIVE LOGITS
    omo
    0.30
    FindObject
    0.29
    aru
    0.28
    sonian
    0.27
    èĢģçĪ¸
    0.26
    obil
    0.25
     Expanded
    0.24
    襲
    0.24
    ijo
    0.24
    ood
    0.24
    Activations Density 0.009%

    No Known Activations