© 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. 108080
    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
    æ°ijå¿ĥ
    -0.31
    SelectedItem
    -0.28
    æĬķåħ¥
    -0.27
    Ñģел
    -0.26
    ingleton
    -0.26
    éĩĮç¨ĭç¢ij
    -0.26
    決ãĤģ
    -0.25
     Chlor
    -0.25
    åľ°æłĩ
    -0.25
     programma
    -0.24
    POSITIVE LOGITS
    ëĭī
    0.28
    ç²ī
    0.27
    åħ¶
    0.26
    åı£æ°Ķ
    0.26
     Rank
    0.25
    宽
    0.25
     does
    0.25
    nez
    0.23
    åIJĪæ³ķ
    0.23
    iano
    0.23
    Activations Density 1.235%

    No Known Activations

    This feature has no known activations.