© 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. 108504
    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
    IPP
    -0.30
    éĦ¯
    -0.26
    å·¥èīºåĵģ
    -0.26
    è¿Ļ份
    -0.25
    车åŃIJ
    -0.25
    æĶ¶è´¹æłĩåĩĨ
    -0.25
    ä½ľåĵģåĨħ容
    -0.25
    æŃ£åĵģ
    -0.25
    opped
    -0.24
    Scenario
    -0.24
    POSITIVE LOGITS
    åĪĩ
    0.30
    éħį
    0.26
    ;↵
    0.26
     Que
    0.26
    缸ç»ĵåIJĪ
    0.26
    å¼Ģ
    0.25
    åĽ
    0.25
     que
    0.25
    å·¥ä½ľä¼ļè®®
    0.25
    è§ģ
    0.24
    Activations Density 0.886%

    No Known Activations

    This feature has no known activations.