© 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. 107596
    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
     Redistributions
    -0.28
    éĵ¡
    -0.25
    stances
    -0.25
    纩
    -0.25
    iler
    -0.25
    æĭĴçµķ
    -0.24
    éŀ«
    -0.24
     Prä
    -0.24
     gratuites
    -0.24
    lies
    -0.24
    POSITIVE LOGITS
    çľĭäºĨä¸Ģ
    0.31
    æĿĥåĪ©
    0.26
     negligent
    0.26
    omer
    0.25
    /Foundation
    0.25
    cerpt
    0.25
    éľ²
    0.25
    oles
    0.24
    é¢ł
    0.24
    æ´»æĢ§
    0.24
    Activations Density 0.914%

    No Known Activations

    This feature has no known activations.