© 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. 109149
    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
    set
    -0.29
     vs
    -0.28
     member
    -0.26
     NA
    -0.26
     =
    -0.25
    çIJĽ
    -0.25
     tie
    -0.25
     ingredient
    -0.24
    there
    -0.24
    vs
    -0.24
    POSITIVE LOGITS
    ĶåĽŀ
    0.25
    lius
    0.25
    ivy
    0.25
    è¾¾æłĩ
    0.25
    aniem
    0.25
    è¿ĩåħ³
    0.24
    ç´ł
    0.24
    entai
    0.24
    äºļ马éĢĬ
    0.24
    pery
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.