© 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. 35-TRANSCODER-HP
    7. 39021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¤Ģ
    -0.30
    æŶéĹ´åĨħ
    -0.28
    岬
    -0.28
    ç«ŀäºīä¼ĺåĬ¿
    -0.26
    次ä¼ļè®®
    -0.25
    CONTEXT
    -0.25
    å¥¥åľ°
    -0.25
     ton
    -0.25
     sequence
    -0.25
    æŁĬ
    -0.25
    POSITIVE LOGITS
    á»ģ
    0.30
    è¿ĻéĩĮ
    0.28
    ä¸ŃåĽ½
    0.28
    缴
    0.28
    ะ
    0.27
    å¤ļ
    0.26
    inati
    0.26
    bench
    0.25
    —they
    0.25
    èĭ¦
    0.25
    Activations Density 3.224%

    No Known Activations

    This feature has no known activations.