© 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. 32-TRANSCODER-HP
    7. 41530
    Prev
    Next
    INDEX
    Explanations

    cer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fou
    -0.28
    len
    -0.27
     pointer
    -0.26
    éĢ¡
    -0.25
    ilst
    -0.24
     PTR
    -0.24
    (itemView
    -0.24
    oline
    -0.24
    åŁķ
    -0.24
    ubby
    -0.24
    POSITIVE LOGITS
    讲
    0.31
    ç½Ĺ
    0.30
     ham
    0.29
    è¬Ľ
    0.27
    ç¡Ŀ
    0.27
    æĽ¿
    0.27
    umi
    0.26
    -call
    0.26
     voc
    0.26
    auty
    0.25
    Activations Density 0.000%

    No Known Activations