© 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. 32-TRANSCODER-HP
    7. 42360
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Road
    -0.39
    çĻ½
    -0.38
     document
    -0.38
    mile
    -0.38
     road
    -0.37
     Deliver
    -0.37
     documents
    -0.35
     deliver
    -0.35
    Road
    -0.35
     Document
    -0.35
    POSITIVE LOGITS
    åĪĽéĢłäºĨ
    0.28
     giveaway
    0.26
    orth
    0.26
    å§ijå¨ĺ
    0.24
     Favorite
    0.24
     zones
    0.24
    ongsTo
    0.23
    èļ¤
    0.23
    terior
    0.23
    ords
    0.23
    Activations Density 0.006%

    No Known Activations