© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11139
    Prev
    Next
    INDEX
    Explanations

    birth dates and names

    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
    ä½Ĩæĺ¯å¯¹äºİ
    -0.10
    AGO
    -0.08
     Moran
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.08
    شع
    -0.08
     dip
    -0.08
    榻
    -0.08
    -sk
    -0.08
     Alf
    -0.08
    çĻ¾å§ĵ
    -0.08
    POSITIVE LOGITS
    è¹Ń
    0.13
    æķħ乡
    0.11
    èķ¤
    0.09
    åħĴ
    0.09
    uv
    0.08
    书é¦Ļ
    0.08
    èij³
    0.08
    Republicans
    0.08
    èĮĶ
    0.08
    åº
    0.08
    Activations Density 0.118%

    No Known Activations