© 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. 129588
    Prev
    Next
    INDEX
    Explanations

    spill

    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
    presso
    -0.29
    onnen
    -0.24
    ãģ¹ãģį
    -0.23
    åįģ足
    -0.23
    gee
    -0.23
    ger
    -0.23
    绣
    -0.23
    åħŃ大
    -0.22
     Autos
    -0.22
    tram
    -0.22
    POSITIVE LOGITS
    lic
    0.31
    resents
    0.30
    licity
    0.30
    ulate
    0.28
    ist
    0.27
    æķĻè®Ń
    0.27
    iation
    0.26
     estr
    0.25
    weed
    0.25
     reason
    0.25
    Activations Density 0.083%

    No Known Activations