© 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. 108536
    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
     bay
    -0.30
    qry
    -0.27
    rag
    -0.27
    æŃ£å¼ı
    -0.26
    onia
    -0.26
    éĩįå¿ĥ
    -0.25
    -screen
    -0.25
    æħ°éĹ®
    -0.25
    æݢ访
    -0.24
    endale
    -0.24
    POSITIVE LOGITS
    acles
    0.30
    çĶ¨æĪ·æıIJä¾Ľ
    0.27
    unker
    0.26
     volum
    0.26
     liv
    0.26
    ictures
    0.26
    ism
    0.24
    æ½ľèīĩ
    0.24
    èĵĭ
    0.24
    ãĥĹãĥ©ãĥ³
    0.24
    Activations Density 1.071%

    No Known Activations

    This feature has no known activations.