© 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. 23666
    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
    iqué
    -0.33
     stretch
    -0.32
     pel
    -0.26
    å½»
    -0.26
     unthinkable
    -0.25
    uce
    -0.25
    visión
    -0.25
     unw
    -0.25
    é³ŀ
    -0.24
    å¾¹
    -0.24
    POSITIVE LOGITS
    åĵķ
    0.30
    åįİçĽĽé¡¿
    0.30
    端
    0.26
    çªĹå¤ĸ
    0.25
    dob
    0.25
    bery
    0.25
    дол
    0.25
    Dod
    0.24
    Ended
    0.23
    endl
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.