© 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. 23-TRANSCODER-HP
    7. 23769
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waves
    -0.28
    大
    -0.27
     borne
    -0.27
     born
    -0.27
     birth
    -0.26
    åľ£
    -0.26
    çļĦä¸ľè¥¿
    -0.25
    ä¸ŃçļĦ
    -0.25
    -wh
    -0.25
     success
    -0.25
    POSITIVE LOGITS
    LOUR
    0.29
    rete
    0.28
    ariat
    0.28
    olla
    0.28
    æ®Ħ
    0.27
    @a
    0.27
    cheon
    0.27
    rets
    0.27
    ureau
    0.27
    =top
    0.26
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.