© 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. 24-TRANSCODER-HP
    7. 150527
    Prev
    Next
    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人æ°Ķ
    -0.26
    icle
    -0.26
    çļĦè¿ĩç¨ĭä¸Ń
    -0.26
    人å¿ĥ
    -0.25
    centration
    -0.25
     vitae
    -0.25
    æ°Ķè´¨
    -0.25
     concentration
    -0.25
    çļĦèīºæľ¯
    -0.24
    riel
    -0.24
    POSITIVE LOGITS
    erie
    0.30
    hashCode
    0.30
    ECH
    0.28
    äºĶ个
    0.25
    CAN
    0.25
    APE
    0.25
     Cellular
    0.25
    markets
    0.25
    ä¸Ģå¹´
    0.24
     Agenda
    0.24
    Activations Density 0.901%

    No Known Activations