© 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. 149820
    Prev
    Next
    INDEX
    Explanations

    Strings and names

    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
    æĿĤ
    -0.27
    驳
    -0.26
    ç«ŀ
    -0.26
    æŀľçĦ¶
    -0.26
    å¾Ģå¾Ģ
    -0.25
     dú
    -0.25
    å¼Ĥ
    -0.25
    å¼¹
    -0.25
    å¾Ģå¾Ģä¼ļ
    -0.24
    -ts
    -0.24
    POSITIVE LOGITS
    ols
    0.31
    ley
    0.26
     Arms
    0.25
    ella
    0.25
    Keeper
    0.24
    headed
    0.24
    强奸
    0.23
    大åĨĽ
    0.23
    lov
    0.23
    IsRequired
    0.23
    Activations Density 0.122%

    No Known Activations