© 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. 21658
    Prev
    Next
    INDEX
    Explanations

    part or region 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
    å¨ģ
    -0.10
    ongo
    -0.09
    lane
    -0.09
    ä¸ĩ象
    -0.09
    å±ŀ
    -0.08
    éļĶ
    -0.08
     зÑĥб
    -0.08
    ç¾Ĭ
    -0.08
    åĿŁ
    -0.08
    åij½
    -0.08
    POSITIVE LOGITS
    éĥ¨ä½į
    0.19
    ä¸Ģå¤Ħ
    0.18
     areas
    0.18
    ä¹ĭå¤Ħ
    0.16
     spots
    0.16
    åľ°æĸ¹
    0.15
    areas
    0.15
     меÑģÑĤа
    0.14
    å¤Ħ
    0.14
    çļĦåľ°æĸ¹
    0.14
    Activations Density 0.416%

    No Known Activations