© 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. 108617
    Prev
    Next
    INDEX
    Explanations

    Diagrams and circuits

    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
    oron
    -0.27
     hung
    -0.25
    .appendTo
    -0.25
    TypeEnum
    -0.24
    onest
    -0.24
    å¢ŀéĩı
    -0.24
    _subtype
    -0.24
    éĴ¦
    -0.24
    ertype
    -0.24
    egrity
    -0.24
    POSITIVE LOGITS
     diagram
    0.38
    åĽ¾åĥı
    0.37
    åĽ¾
    0.37
    åĽ¾ä¸º
    0.33
    çļĦçħ§çīĩ
    0.31
     image
    0.30
    åĽ¾çīĩ
    0.29
    LLU
    0.27
     diagrams
    0.27
    çļĦåºĶçĶ¨
    0.27
    Activations Density 0.119%

    No Known Activations