© 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. 25-TRANSCODER-HP
    7. 109281
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨åĪĨåĨħ容
    -0.31
    çĥŃ度
    -0.30
    å·²æľī
    -0.27
     NAN
    -0.27
    ETO
    -0.26
    legation
    -0.26
    rac
    -0.26
    ixin
    -0.25
    -rad
    -0.25
    å»¶æľŁ
    -0.25
    POSITIVE LOGITS
    onest
    0.28
    æĬĬä»ĸ
    0.27
    .alibaba
    0.27
    merge
    0.27
    æIJ¬
    0.26
    æıĦ
    0.26
    .merge
    0.26
    аниÑĨ
    0.25
     merge
    0.25
    fore
    0.25
    Activations Density 0.974%

    No Known Activations

    This feature has no known activations.