© 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. 39178
    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
    æ³ľ
    -0.30
    å©ł
    -0.29
    trägt
    -0.28
    APT
    -0.27
    traî
    -0.27
    身å¿ĥåģ¥åº·
    -0.27
    ège
    -0.27
    æīŃ转
    -0.26
    åIJĦçķĮ
    -0.26
    è§īéĨĴ
    -0.26
    POSITIVE LOGITS
    è¿ĩ大
    0.32
    }↵↵↵↵↵
    0.29
    é£İ
    0.27
    }↵↵↵↵↵↵
    0.27
    éľ²
    0.26
    ,...↵↵
    0.26
     material
    0.26
     compass
    0.26
     un
    0.26
    ãĢį↵↵
    0.25
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.