© 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. 112141
    Prev
    Next
    INDEX
    Explanations

    showing or indicating

    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
    çļĦ身份
    -0.25
    âĹ¯
    -0.25
    (ur
    -0.25
    exact
    -0.24
    çļĦ表çİ°
    -0.24
    Representation
    -0.24
     tre
    -0.23
     whipped
    -0.23
     treasure
    -0.23
     Wh
    -0.23
    POSITIVE LOGITS
    yre
    0.29
    clud
    0.29
    ings
    0.27
    .conf
    0.27
    ants
    0.25
    çĿĢä»ĸ
    0.25
     Conf
    0.25
    ç¬Ħ
    0.24
    GRES
    0.24
    ances
    0.23
    Activations Density 0.029%

    No Known Activations