© 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. 88101
    Prev
    Next
    INDEX
    Explanations

    forum/question-answer context

    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
    hei
    -0.27
    lotte
    -0.26
    atte
    -0.25
    bef
    -0.25
    blocked
    -0.25
    èĤ¼
    -0.24
     Bundy
    -0.23
    enate
    -0.23
    onta
    -0.23
     Laf
    -0.23
    POSITIVE LOGITS
    温馨æıIJ示
    0.25
    åľ¬
    0.25
    ç½ij
    0.23
    éĶĦ
    0.23
     sure
    0.23
    è¡¥åĬ©
    0.23
    à¸Ķา
    0.23
    вен
    0.22
    ä¸Ģç±»
    0.22
    .wordpress
    0.22
    Activations Density 0.003%

    No Known Activations