© 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. 39568
    Prev
    Next
    INDEX
    Explanations

    block and bitcoin

    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
    ä¸ĭåįĬ
    -0.09
    æ¯ħ
    -0.09
    _VALUES
    -0.09
    æ¿
    -0.09
    -spacing
    -0.08
    å¹³åĩ¡
    -0.08
    åı»
    -0.08
    ammo
    -0.08
    .Override
    -0.08
    POSITIVE LOGITS
    çĻ¾èĬ±
    0.10
    æĴ®
    0.10
    çļ±çº¹
    0.09
    ä»»æķĻ
    0.09
    ToLocal
    0.09
    æĭ±
    0.09
    ç»İ
    0.09
    åķĨæĪ·
    0.08
    backs
    0.08
    稼
    0.08
    Activations Density 0.111%

    No Known Activations