© 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. 109267
    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
    hte
    -0.25
     crt
    -0.25
    odem
    -0.25
    erspective
    -0.25
     rely
    -0.24
     Kear
    -0.24
     pyt
    -0.24
     nailed
    -0.24
    cem
    -0.24
    åĿļ飧
    -0.24
    POSITIVE LOGITS
    详
    0.26
    wich
    0.25
    ÐIJÐŀ
    0.25
    åı¯èĥ½åıijçĶŁ
    0.25
     elim
    0.25
     INST
    0.24
    necessary
    0.24
    æĿ¡
    0.24
    *)
    0.24
    çļĩåĨł
    0.24
    Activations Density 0.117%

    No Known Activations

    This feature has no known activations.