© 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. 25-TRANSCODER-HP
    7. 108057
    Prev
    Next
    INDEX
    Explanations

    causing or spurring action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jako
    -0.28
     Signed
    -0.25
     Pee
    -0.24
    代è¨Ģ
    -0.24
     Cru
    -0.23
     mpl
    -0.23
     alarmed
    -0.23
     eÄŁer
    -0.23
     Stored
    -0.23
     Mann
    -0.22
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.31
    -away
    0.28
    inka
    0.28
    åĩºåĬ¨
    0.27
    çİ°å®ŀ
    0.27
    çݰ代åĮĸ
    0.26
    abouts
    0.26
    iances
    0.25
    翼
    0.24
    lean
    0.24
    Activations Density 0.089%

    No Known Activations