© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    letter grades

    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
    亲
    -0.29
    -sharing
    -0.26
    wand
    -0.25
     yat
    -0.25
    çļĦç²¾ç¥ŀ
    -0.25
    æ¯ķä¸ļ
    -0.25
     dagger
    -0.25
     distraction
    -0.24
    缨
    -0.24
    .datab
    -0.24
    POSITIVE LOGITS
    åŀĽ
    0.27
    ough
    0.27
     rev
    0.26
    ãĤĤãĤīãģĪ
    0.25
    antage
    0.25
    endant
    0.25
    è´»
    0.25
    å®ļçĤ¹
    0.24
    çķ¶çĦ¶
    0.24
    åłĨ
    0.24
    Activations Density 0.001%

    No Known Activations