© 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. 9-TRANSCODER-HP
    7. 29434
    Prev
    Next
    INDEX
    Explanations

    differentiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮºåĪ«
    -0.38
     distinct
    -0.37
     distingu
    -0.36
     distinguish
    -0.36
     distinction
    -0.34
    åĮºåĪĨ
    -0.34
    çļĦåĮºåĪ«
    -0.31
     distinctive
    -0.30
     distinctions
    -0.30
    istingu
    -0.30
    POSITIVE LOGITS
    ç¾°
    0.25
    DDS
    0.25
     Synd
    0.25
    /values
    0.24
    Framework
    0.24
     ),↵↵
    0.24
    æĺĮ
    0.24
     pitching
    0.24
    RH
    0.24
    /messages
    0.23
    Activations Density 3.466%

    No Known Activations