© 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. 107350
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    çīĪæľ¬
    -0.25
    .twitter
    -0.25
    åIJĮç±»
    -0.24
     version
    -0.24
    acula
    -0.24
     bun
    -0.24
     sponsored
    -0.24
    RESSED
    -0.23
    ware
    -0.23
    .finish
    -0.23
    POSITIVE LOGITS
    äºİ
    0.30
     Tra
    0.25
     colors
    0.25
    éģĵçIJĨ
    0.25
    åĨĻçĿĢ
    0.25
    ian
    0.24
    areas
    0.24
    çĥŃæ°´
    0.24
    .Criteria
    0.24
    .Area
    0.23
    Activations Density 0.908%

    No Known Activations