© 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. 108939
    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
     orn
    -0.29
     ban
    -0.26
    kr
    -0.25
     hub
    -0.25
     signatures
    -0.25
    Ban
    -0.25
    k
    -0.25
     lum
    -0.24
     polar
    -0.24
     task
    -0.24
    POSITIVE LOGITS
    elor
    0.28
    åĪĩ
    0.28
    åij¨åĽ´
    0.28
    éĻĦè¿ij
    0.27
    ä½ıåĿĢ
    0.27
    åŁ¹è®ŃæľºæŀĦ
    0.27
    é£İ鼨
    0.27
    æĢİä¹ĪåĽŀäºĭ
    0.27
    è¿ĻäºĽéĹ®é¢ĺ
    0.26
    ZE
    0.26
    Activations Density 3.305%

    No Known Activations

    This feature has no known activations.