© 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. 25490
    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
    Negative Logits
    krit
    -0.27
    –↵↵
    -0.27
    _interp
    -0.26
     Invent
    -0.26
    _SUBJECT
    -0.24
    _sentence
    -0.24
    /trunk
    -0.24
    (Base
    -0.23
     BaseModel
    -0.23
    åı¶çīĩ
    -0.23
    POSITIVE LOGITS
    èµĮ
    0.30
    åĸ±
    0.27
     widget
    0.27
    èµĶ
    0.26
     gamble
    0.25
    åĨĴéĻ©
    0.25
    [..
    0.25
    çĽ¸ä¼´
    0.24
     Darling
    0.24
    nr
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.