© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    from to

    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
    èĿ®
    -0.09
    çļĦåľŁåľ°
    -0.09
    orney
    -0.08
    对åħ¶è¿Ľè¡Į
    -0.08
    è¿Ļæł·ä¸Ģ个
    -0.08
    iba
    -0.08
    çĬ¶åĨµ
    -0.08
    æĪ¿éĹ´éĩĮ
    -0.08
    1
    -0.07
    æĥħåĨµä¸ĭ
    -0.07
    POSITIVE LOGITS
    /or
    0.10
    /OR
    0.10
    aso
    0.09
    ators
    0.09
    ppers
    0.09
    è¿Ļå°±
    0.08
     XK
    0.08
    èĪªçº¿
    0.08
    æķŀ
    0.08
    åĽ½æĥħ
    0.08
    Activations Density 0.146%

    No Known Activations