© 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. 41487
    Prev
    Next
    INDEX
    Explanations

    network data transmitting

    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
     stream
    -0.31
     Stream
    -0.30
    bac
    -0.28
    Stream
    -0.27
    书ä¸Ń
    -0.26
     rem
    -0.26
    _stream
    -0.25
    Book
    -0.25
    stream
    -0.25
    -book
    -0.25
    POSITIVE LOGITS
    oser
    0.32
     Pe
    0.28
     Patri
    0.26
    Pe
    0.26
    ape
    0.25
     pe
    0.25
     anonymous
    0.24
     edge
    0.24
    æķ°æį®
    0.24
    åĪ°åľº
    0.24
    Activations Density 0.002%

    No Known Activations