© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107488
    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
    orative
    -0.27
    æ³½
    -0.27
     Kore
    -0.27
    Ñģка
    -0.26
    owers
    -0.25
    ROLLER
    -0.25
    ç©Ĺ
    -0.25
    apas
    -0.24
     bosses
    -0.24
    eries
    -0.24
    POSITIVE LOGITS
    -on
    0.28
     Frid
    0.27
    @m
    0.27
    icated
    0.25
     matching
    0.25
    -On
    0.24
    éĺ´éĺ³
    0.23
    éĤ£åĦ¿
    0.23
    ä¸įåIJĪæł¼
    0.23
     devis
    0.23
    Activations Density 0.899%

    No Known Activations

    This feature has no known activations.