© 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. 42461
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions and negations

    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
    æºĸ
    -0.30
    plat
    -0.30
    羣
    -0.28
    夷
    -0.28
    rop
    -0.26
    вал
    -0.26
    è¿Ļéĥ¨åĪĨ
    -0.26
    åĩĨ
    -0.25
    posal
    -0.24
     zug
    -0.24
    POSITIVE LOGITS
     read
    0.34
    cÃŃ
    0.28
    :].
    0.27
    -read
    0.27
    	read
    0.26
    读
    0.26
    绣çŃ¹æİ¨è¿Ľ
    0.26
     Pey
    0.25
    .read
    0.25
    æĢ»ç»ĵ
    0.25
    Activations Density 0.000%

    No Known Activations