© 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. 57792
    Prev
    Next
    INDEX
    Explanations

    Northwest Passage

    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
     оÑĤзÑĭв
    -0.10
     ì¤Ģ
    -0.09
    nej
    -0.09
    .pad
    -0.08
    éŃģ
    -0.08
    angen
    -0.08
    velt
    -0.08
     MGM
    -0.08
    èľķ
    -0.08
    ä¿ļ
    -0.08
    POSITIVE LOGITS
    æ°´åŁŁ
    0.09
     Parliamentary
    0.09
    åī©ä¸ĭ
    0.09
    棱
    0.09
    åŀĤ
    0.09
    åī©
    0.09
    éĿĸ
    0.09
    楫
    0.08
     Stevens
    0.08
    æIJľæķij
    0.08
    Activations Density 0.100%

    No Known Activations