© 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. 108458
    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
    _consum
    -0.26
     Spiel
    -0.25
    æĪijå¿ĥéĩĮ
    -0.24
    [attr
    -0.24
     condem
    -0.23
    _splits
    -0.23
     moving
    -0.23
     at
    -0.23
     Solutions
    -0.23
     solutions
    -0.23
    POSITIVE LOGITS
    ettings
    0.27
    ä»Ģä¹Īåij¢
    0.26
    æ¤ģ
    0.25
    CRET
    0.25
    åıĺ
    0.24
    æĻĭ
    0.24
    èİ«æĸ¯
    0.24
    aspect
    0.24
    cx
    0.24
    ä»Ĩ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.