© 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. 43440
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    otted
    -0.28
     repro
    -0.27
    peg
    -0.27
    è¯ģå®ŀ
    -0.27
    oted
    -0.26
    earer
    -0.26
    prove
    -0.25
     proof
    -0.25
    owa
    -0.25
    æ¦ľ
    -0.24
    POSITIVE LOGITS
    è¿Ŀ
    0.27
    çļĦçŁ¥è¯Ĩ
    0.26
    维度
    0.25
    ðŁı½
    0.25
     Swim
    0.25
    ä¸ĵä¸ļä»İäºĭ
    0.24
    åł¤
    0.24
    çµIJ
    0.23
    ç¼°
    0.23
     Glock
    0.23
    Activations Density 0.003%

    No Known Activations