© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58395
    Prev
    Next
    INDEX
    Explanations

    dog sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĥ°
    -0.09
     vert
    -0.08
    .getConfig
    -0.08
    ule
    -0.08
     Ñıв
    -0.08
    .getItems
    -0.08
    躲
    -0.08
    å¤Ķ
    -0.08
    豪
    -0.08
     illusion
    -0.08
    POSITIVE LOGITS
    声åĵį
    0.10
    æĻ¦
    0.10
    è·Ŀ
    0.09
    åįģ大
    0.09
    éģ¥
    0.09
    ç¥ī
    0.08
    æ¾ľ
    0.08
    主è¦ģåİŁåĽł
    0.08
    ISP
    0.08
    å°¼äºļ
    0.08
    Activations Density 0.022%

    No Known Activations