© 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. 150175
    Prev
    Next
    INDEX
    Explanations

    more

    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
    ly
    -0.27
    çļĦ第ä¸Ģ个
    -0.27
    /ns
    -0.26
     massa
    -0.26
    arl
    -0.25
    ÑĪка
    -0.25
    人çļĦ
    -0.24
     senses
    -0.24
     callbacks
    -0.24
    çļĦ第ä¸Ģ
    -0.24
    POSITIVE LOGITS
    igraph
    0.27
     eens
    0.25
    udent
    0.25
    theValue
    0.25
    ActionCode
    0.25
    å¶Ļ
    0.25
    .opens
    0.25
    enties
    0.25
    .usage
    0.24
    纯
    0.24
    Activations Density 1.000%

    No Known Activations