© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22254
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific language

    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
    à¸ķรา
    -0.27
    ighth
    -0.27
    keh
    -0.26
     racially
    -0.25
    ừ
    -0.25
     Frem
    -0.25
    SimpleName
    -0.24
    acha
    -0.24
     nad
    -0.24
     Freeman
    -0.24
    POSITIVE LOGITS
    æĻļéĹ´
    0.28
     Kov
    0.28
    éķ«
    0.27
    æĶ¾å¤§
    0.26
    éĺħ读
    0.26
    èĨ¨
    0.26
    室åĨħ
    0.26
     blogging
    0.26
    DOCUMENT
    0.25
    éĢĢ
    0.25
    Activations Density 0.003%

    No Known Activations