© 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. 35-TRANSCODER-HP
    7. 38947
    Prev
    Next
    INDEX
    Explanations

    be

    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
     BBB
    -0.30
     RTP
    -0.30
    /photo
    -0.30
     Ducks
    -0.29
     Homepage
    -0.29
     ATS
    -0.29
     Gundam
    -0.29
     Burger
    -0.29
     Leafs
    -0.28
     SCC
    -0.28
    POSITIVE LOGITS
    form
    0.40
    built
    0.38
    be
    0.38
    both
    0.37
    hidden
    0.36
    post
    0.36
    closed
    0.36
    par
    0.35
    get
    0.35
    count
    0.35
    Activations Density 14.700%

    No Known Activations