© 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. 22-TRANSCODER-HP
    7. 130556
    Prev
    Next
    INDEX
    Explanations

    -season

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     **↵
    -0.30
    baugh
    -0.28
    perse
    -0.27
    ennial
    -0.27
     "\(
    -0.25
    AndGet
    -0.25
    erva
    -0.24
    Them
    -0.23
    ngoing
    -0.23
     keyed
    -0.23
    POSITIVE LOGITS
     joining
    0.28
    iline
    0.28
    éĩİ
    0.25
    .hu
    0.24
    join
    0.24
    åŃij
    0.24
     joins
    0.24
    ilen
    0.24
     hand
    0.23
    ville
    0.23
    Activations Density 0.011%

    No Known Activations