© 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. 4593
    Prev
    Next
    INDEX
    Explanations

    words ending in 'berry' or 'belle'

    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
     jon
    -0.09
    éĵ¨
    -0.09
    pond
    -0.09
    è´µ
    -0.09
    è²´
    -0.08
    稽
    -0.08
    heet
    -0.08
    éĺ¶
    -0.08
    éĺĬ
    -0.08
    åĩºçĤī
    -0.08
    POSITIVE LOGITS
    ÑĤал
    0.10
    ENCE
    0.10
    河边
    0.10
    éĢ®
    0.10
    åİļ
    0.09
    rette
    0.09
    ioned
    0.09
    âĸ¾
    0.09
    å¿Į
    0.09
    ivated
    0.08
    Activations Density 0.011%

    No Known Activations