© 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. 107468
    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
    è¡Į
    -0.27
     Breath
    -0.27
    BT
    -0.27
    èķī
    -0.26
    isa
    -0.26
    Capacity
    -0.26
    åı£æ°Ķ
    -0.25
    bour
    -0.24
    åı¦ä¸ĢåįĬ
    -0.24
    对éĿ¢
    -0.24
    POSITIVE LOGITS
    æĸ¯å¡Ķ
    0.28
    odium
    0.27
    éļ¶å±ŀ
    0.26
    [opt
    0.25
    tsky
    0.25
    被æ·ĺæ±°
    0.25
     insol
    0.24
    åİļéĩį
    0.24
    eras
    0.24
    èį¯åºĹ
    0.23
    Activations Density 1.070%

    No Known Activations

    This feature has no known activations.