© 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. 9732
    Prev
    Next
    INDEX
    Explanations

    es followed by other tokens

    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
    ings
    -0.11
    à¹Į
    -0.10
    edList
    -0.10
    edly
    -0.10
    ள
    -0.09
    amp
    -0.08
    ãģķãĤī
    -0.08
     Seah
    -0.08
    åĩłä¹İæīĢæľī
    -0.08
    ths
    -0.08
    POSITIVE LOGITS
    oteric
    0.12
    pecially
    0.12
    ionage
    0.11
    ablish
    0.10
    oter
    0.09
    ential
    0.09
    æĢ¥
    0.09
    	TokenName
    0.09
    ftware
    0.09
    rection
    0.09
    Activations Density 0.051%

    No Known Activations