© 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. 51043
    Prev
    Next
    INDEX
    Explanations

    view of

    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
    Ã¤ÃŁ
    -0.09
    æį»
    -0.09
    æĹłå£°
    -0.08
    笪
    -0.08
    ä½ĵåĪ¶
    -0.08
    åĩºåĽ½çķĻåѦ
    -0.08
     SCI
    -0.08
    飧
    -0.07
    æıIJ示
    -0.07
    assel
    -0.07
    POSITIVE LOGITS
     view
    0.20
    è§Ĩè§Ĵ
    0.19
    çľĭæ³ķ
    0.17
     perspective
    0.16
    è§ĤçĤ¹
    0.15
    view
    0.14
     views
    0.14
    	view
    0.14
    çľĭå¾ħ
    0.14
    .view
    0.14
    Activations Density 0.091%

    No Known Activations