© 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. 23940
    Prev
    Next
    INDEX
    Explanations

    viruses

    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
    çĪ¿
    -0.30
    åħļç»Ħ
    -0.28
    æŀľæłij
    -0.25
    кеÑĢ
    -0.25
    åħ¨éķ¿
    -0.24
    çĥĺ
    -0.24
     Goose
    -0.24
     commerc
    -0.24
    sizes
    -0.24
    stüt
    -0.23
    POSITIVE LOGITS
    çĻ¾
    0.27
    æ¶Īæ¯Ĵ
    0.27
     qu
    0.27
    zu
    0.26
     Olympia
    0.26
    ä¾®
    0.25
    QUE
    0.25
    æł·æľ¬
    0.25
    ibs
    0.25
    yla
    0.25
    Activations Density 0.000%

    No Known Activations