© 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. 56294
    Prev
    Next
    INDEX
    Explanations

    image .setImageResource .getImage

    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
    иÑĪ
    -0.11
    ouse
    -0.09
    çĸıéĢļ
    -0.09
    uber
    -0.09
    ä¸į让
    -0.09
    uiten
    -0.08
    è¿IJ转
    -0.08
    asant
    -0.08
    åİļåİļ
    -0.08
    ieg
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¹ħ
    0.12
     hÆ°á»Łng
    0.12
    .setImageResource
    0.11
    .githubusercontent
    0.10
    ä¸Ģå¼ł
    0.10
    .getImage
    0.10
    æ¤Ĵ
    0.09
    è½°çĤ¸
    0.09
    çļĦæĸĩåŃĹ
    0.09
    è´´
    0.09
    Activations Density 0.186%

    No Known Activations