© 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. 23905
    Prev
    Next
    INDEX
    Explanations

    New

    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
    xcf
    -0.27
    ä¿Ŀè¯ģ
    -0.26
    é»Ŀ
    -0.26
    èĴ½
    -0.25
    uste
    -0.25
    æīij
    -0.24
     backwards
    -0.24
    olare
    -0.24
    æľĹ
    -0.24
    å´Ĩ
    -0.24
    POSITIVE LOGITS
    ovies
    0.26
    çĻ¾åIJĪ
    0.26
    itel
    0.25
    boro
    0.24
    itelist
    0.24
     ..........
    0.24
    +"</
    0.24
    itur
    0.23
    annes
    0.23
    æĿ¥äºĨ
    0.23
    Activations Density 0.024%

    No Known Activations