© 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. 108350
    Prev
    Next
    INDEX
    Explanations

    to

    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
    æīĢéľĢè¦ģ
    -0.41
     needed
    -0.40
     required
    -0.37
    éľĢè¦ģ
    -0.35
    æīĢéľĢè¦ģçļĦ
    -0.35
     requiring
    -0.34
     require
    -0.34
    éľĢè¦ģçĶ¨
    -0.33
    required
    -0.33
    _needed
    -0.32
    POSITIVE LOGITS
    èĩ¾
    0.32
    istem
    0.29
    (wait
    0.29
     wait
    0.29
     resort
    0.28
    éĿ¢å¯¹
    0.28
     <!--[
    0.28
     lòng
    0.27
    éĿ¢å°į
    0.27
    burgh
    0.27
    Activations Density 1.274%

    No Known Activations