© 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. 22674
    Prev
    Next
    INDEX
    Explanations

    on

    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
    iphy
    -0.29
    æľĭåıĭ们
    -0.27
    emes
    -0.27
    综åIJĪæķ´æ²»
    -0.26
     diy
    -0.26
    idget
    -0.25
     scrapped
    -0.25
    弨
    -0.24
     Blaze
    -0.24
    emodel
    -0.24
    POSITIVE LOGITS
    una
    0.26
    èģĶåIJĪ
    0.24
     IPs
    0.24
    çĦ¦
    0.24
    èĥĮçĿĢ
    0.24
    PAD
    0.24
     Valle
    0.23
    zn
    0.23
    -L
    0.23
    .literal
    0.23
    Activations Density 0.000%

    No Known Activations