© 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. 57334
    Prev
    Next
    INDEX
    Explanations

    looks like / looks to / looks as / looks the

    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
    路桥
    -0.10
    æĥ³ä¸įåĪ°
    -0.09
    aris
    -0.09
    elp
    -0.09
    失èIJ½
    -0.09
    æĴ¤ç¦»
    -0.08
    _license
    -0.08
    ardy
    -0.08
    çł¾
    -0.08
    è¸ı
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻ
    0.10
    å±ĬæŶ
    0.09
    åĪ°æŶåĢĻ
    0.09
    _IOC
    0.09
    ADI
    0.09
    çļĦå°±æĺ¯
    0.08
    ç«ĭå¿Ĺ
    0.08
     пÑĢидеÑĤÑģÑı
    0.08
    inqu
    0.08
    หว
    0.08
    Activations Density 0.170%

    No Known Activations