© 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. 107491
    Prev
    Next
    INDEX
    Explanations

    fields of study

    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
    åĮ¡
    -0.27
     availability
    -0.24
    å°±åľ¨
    -0.24
    aqu
    -0.24
     continuum
    -0.24
    å¹´ä¹ĭ
    -0.24
     aux
    -0.23
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§
    -0.23
    æIJľ
    -0.23
     setC
    -0.23
    POSITIVE LOGITS
    оÑĩно
    0.29
    peration
    0.27
     Addison
    0.26
    PYTHON
    0.26
     regrets
    0.25
    .intent
    0.25
    hazi
    0.24
     sno
    0.24
     GENERATED
    0.24
    hausen
    0.23
    Activations Density 0.916%

    No Known Activations