© 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. 42172
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
    0
    -0.41
    ï¼IJ
    -0.36
    âĤĢ
    -0.25
     Scholar
    -0.25
    rarian
    -0.24
    åħ»èĤ²
    -0.24
    ãģĵãģĵãģ¾ãģ§
    -0.24
    .yahoo
    -0.24
    åįģæĿ¡
    -0.23
     yours
    -0.23
    POSITIVE LOGITS
    ÑĢма
    0.26
    继
    0.25
    è¯Ŀ说
    0.24
    avo
    0.24
    -five
    0.23
    asons
    0.23
    оÑĢÑĤ
    0.23
    ritis
    0.23
    åľ°éģĵ
    0.23
     studs
    0.23
    Activations Density 0.013%

    No Known Activations