© 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. 25267
    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
    缺
    -0.28
    缺失
    -0.27
    转载请
    -0.25
     å±
    -0.25
    辩
    -0.25
     disen
    -0.24
    æ¶īåıĬåĪ°
    -0.24
    Oi
    -0.24
    EXTERN
    -0.23
     translator
    -0.23
    POSITIVE LOGITS
    å°ıæŶåīį
    0.26
     spontaneous
    0.26
    èĩªåıij
    0.25
    perial
    0.25
    alar
    0.24
    uras
    0.24
    å¼
    0.24
    èĪ¬
    0.24
    ular
    0.24
    foot
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.