© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    develop a

    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
    MENT
    -0.09
    æİĴæ¯Ĵ
    -0.09
     ÑĩаÑģÑĤÑĮ
    -0.08
    交æ±ĩ
    -0.08
     snapped
    -0.08
     Bundy
    -0.08
    _extensions
    -0.08
    oure
    -0.08
    çľ¯
    -0.08
    инÑĦоÑĢм
    -0.08
    POSITIVE LOGITS
     appropriate
    0.09
    å±ħ家
    0.09
    åIJĪéĢĤ
    0.09
    usal
    0.09
    è¶Ł
    0.09
    äºĨä¸Ģ个
    0.09
    åIJĪçIJĨ
    0.09
    inders
    0.09
     gep
    0.08
    ساء
    0.08
    Activations Density 0.205%

    No Known Activations