© 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. 107391
    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
     direction
    -0.32
    direction
    -0.30
    -direction
    -0.28
     directions
    -0.27
    Direction
    -0.27
    دÙĬ
    -0.27
    usty
    -0.26
    	direction
    -0.26
     director
    -0.26
     dire
    -0.25
    POSITIVE LOGITS
    KG
    0.28
    èĴ¸
    0.27
    è°ĥæķ´
    0.25
    ä¸ĭå·´
    0.25
    ık
    0.24
    **,
    0.24
    è°ĥ
    0.24
    PHA
    0.24
    çļĦçIJĨæĥ³
    0.24
    åĪļ好
    0.23
    Activations Density 0.940%

    No Known Activations

    This feature has no known activations.