© 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. 39961
    Prev
    Next
    INDEX
    Explanations

    prompting user input

    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
    æĭĨ
    -0.10
     Cron
    -0.09
    ql
    -0.09
    å¾®å¦Ļ
    -0.08
    ç©¿è¶Ĭ
    -0.08
     Standing
    -0.08
    _IL
    -0.08
     limb
    -0.08
    è¡£
    -0.08
    å·§
    -0.08
    POSITIVE LOGITS
    æıIJéĨĴ
    0.10
    御
    0.10
    çķĢ
    0.10
    å¾ģæ±Ĥ
    0.10
    ishi
    0.10
    æīĵæī°
    0.10
    (prompt
    0.09
     prompts
    0.09
    强迫
    0.09
    pon
    0.09
    Activations Density 0.205%

    No Known Activations