© 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. 87306
    Prev
    Next
    INDEX
    Explanations

    citizen

    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
    ache
    -0.32
    ison
    -0.30
    ends
    -0.26
    åħĭæĸ¯
    -0.24
    topl
    -0.24
    æĶ»åĬ¿
    -0.23
    onomic
    -0.23
    HR
    -0.23
    tors
    -0.22
    aged
    -0.22
    POSITIVE LOGITS
    arine
    0.26
    ele
    0.25
    esta
    0.24
    findBy
    0.24
     Burk
    0.23
    çĶŁäº§æĢ»åĢ¼
    0.23
     elev
    0.23
    DNA
    0.22
    าà¸ĩ
    0.22
    éĺģ
    0.22
    Activations Density 0.218%

    No Known Activations