© 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. 7141
    Prev
    Next
    INDEX
    Explanations

    collecting personal details

    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
    .CV
    -0.09
    ncy
    -0.08
     inaug
    -0.08
    çŃīçĿĢ
    -0.08
    stown
    -0.08
    è¯ķ
    -0.08
    è¯ķè¡Į
    -0.08
    iences
    -0.08
    vale
    -0.08
    asta
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸ºäºĨ
    0.12
    å°±æĺ¯ä¸ºäºĨ
    0.10
    éķIJ
    0.10
    .Inv
    0.09
    缮çļĦæĺ¯
    0.09
    以便
    0.09
    缮çļĦåľ¨äºİ
    0.09
    prefer
    0.09
    åħij
    0.08
    ä¼ļè®©ä½ł
    0.08
    Activations Density 0.040%

    No Known Activations