© 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. 41375
    Prev
    Next
    INDEX
    Explanations

    dim

    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
    cÃŃ
    -0.31
    åIJĥ
    -0.28
    RON
    -0.27
    åIJijãģį
    -0.26
    æľ¨è´¨
    -0.26
    ç¹ģå¿Ļ
    -0.26
    pper
    -0.25
    ÑĢан
    -0.25
    åĿ³
    -0.25
    ảng
    -0.25
    POSITIVE LOGITS
     dim
    0.38
    (dim
    0.35
    å¾·æĭī
    0.32
     dims
    0.32
    dim
    0.31
     som
    0.31
     Dim
    0.30
     dr
    0.30
    æ²Ī
    0.29
    éĺ´
    0.28
    Activations Density 0.000%

    No Known Activations