© 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. 108607
    Prev
    Next
    INDEX
    Explanations

    h

    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
     hand
    -0.29
    handleChange
    -0.29
    sher
    -0.28
     harb
    -0.28
    -hand
    -0.28
    åĽłæѤ
    -0.27
     hå
    -0.27
    hand
    -0.26
    ķĮ
    -0.26
    help
    -0.26
    POSITIVE LOGITS
     Absolute
    0.26
    å¤ĩçĶ¨
    0.25
    iams
    0.25
    ç»Ŀ对
    0.25
    -relative
    0.25
    absolute
    0.25
    AVAILABLE
    0.25
     mãi
    0.25
    Absolute
    0.25
    ç«
    0.25
    Activations Density 2.734%

    No Known Activations