© 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. 98070
    Prev
    Next
    INDEX
    Explanations

    a and an

    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
    åħ®
    -0.29
    )m
    -0.25
    伶
    -0.24
     Substance
    -0.24
    anean
    -0.23
     appliance
    -0.23
    çĬ¯ç½ª
    -0.23
    obook
    -0.23
    ä¸įçŁ¥éģĵ
    -0.23
    Amy
    -0.23
    POSITIVE LOGITS
    è°ĥ
    0.29
    osit
    0.25
    山路
    0.25
    è°ĥéħį
    0.25
    iles
    0.25
     CONTRIBUT
    0.25
    éĩįè¦ģ
    0.24
     Duo
    0.24
    rió
    0.24
    mesh
    0.24
    Activations Density 0.003%

    No Known Activations