© 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. 57403
    Prev
    Next
    INDEX
    Explanations

    sale and price information

    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
     ÑĤоÑĢ
    -0.09
    ç±
    -0.09
    éĩįä¸Ń
    -0.09
    getSingleton
    -0.09
    æ·±è¿ľ
    -0.09
    åıµ
    -0.09
    第ä¸ĢæŃ¥
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    ollow
    -0.09
    èį¡
    -0.09
    POSITIVE LOGITS
     dra
    0.10
    blink
    0.09
    æ°¸ä¹ħ
    0.09
     permanent
    0.09
     clearance
    0.09
    æīĵæĬĺ
    0.08
     Permanent
    0.08
    åĭ¤å¥ĭ
    0.08
    .percent
    0.08
    sale
    0.08
    Activations Density 0.047%

    No Known Activations