© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19686
    Prev
    Next
    INDEX
    Explanations

    code and configuration definitions

    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
    /or
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    ä¸įä»ħå¦ĤæѤ
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    essel
    -0.08
    èĮľ
    -0.08
     Fry
    -0.08
     пÑĢакÑĤиÑĩеÑģки
    -0.08
    çĽijçĭ±
    -0.08
    åIJ¬å®Į
    -0.08
    POSITIVE LOGITS
    äºĨ个
    0.08
    å¾ģæ±Ĥ
    0.08
    EndInit
    0.08
    äºĭæĥħ
    0.08
    ancement
    0.08
    äºĽ
    0.08
    äºĭçī©
    0.08
    äºĨä¸Ģ个
    0.08
    ×£
    0.08
    ä»Ģä¹Īåij¢
    0.08
    Activations Density 0.403%

    No Known Activations