© 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. 12-TRANSCODER-HP
    7. 22580
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icals
    -0.30
     getInput
    -0.28
    åĭĺ
    -0.28
    itta
    -0.28
    ведениÑı
    -0.28
     Editorial
    -0.27
     charities
    -0.27
     mName
    -0.27
     domination
    -0.26
     upd
    -0.26
    POSITIVE LOGITS
     cach
    0.28
    Iss
    0.27
    flat
    0.26
    _ie
    0.26
    corn
    0.24
    çıĻ
    0.24
     banging
    0.24
    é¢Ĺ
    0.24
     Cooler
    0.24
    æĭ¿åĩº
    0.24
    Activations Density 0.018%

    No Known Activations