© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36600
    Prev
    Next
    INDEX
    Explanations

    content

    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
    æĸ¹åľĨ
    -0.10
    IFI
    -0.10
    è¸
    -0.09
    å®īåħ¨æĦŁ
    -0.09
    _$_
    -0.09
    å®ī举
    -0.09
     refunds
    -0.09
    èĥ¥
    -0.09
    æĶ¹æŃ£
    -0.09
    å®īå®ļ
    -0.08
    POSITIVE LOGITS
     content
    0.16
    ãĤ³ãĥ³ãĥĨãĥ³ãĥĦ
    0.15
    content
    0.14
    åĨħ容
    0.14
    åİŁåĪĽ
    0.14
    Content
    0.13
    UGC
    0.13
    åħ§å®¹
    0.13
    é«ĺè´¨éĩı
    0.12
     Content
    0.12
    Activations Density 0.087%

    No Known Activations