© 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. 58099
    Prev
    Next
    INDEX
    Explanations

    taste, tasted, flavor

    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
    å´©æºĥ
    -0.09
    è§Ĩéĩİ
    -0.09
    erre
    -0.09
    å½¼
    -0.08
    åį¸
    -0.08
    å°ģ
    -0.08
    ä¸Ģå¹ħ
    -0.08
    generation
    -0.08
    äºĨä¸Ģç³»åĪĹ
    -0.08
    Royal
    -0.08
    POSITIVE LOGITS
    æ»ĭåij³
    0.14
    èĦĶ
    0.14
    ä¸Ģåı£
    0.13
     вкÑĥÑģ
    0.11
    åij³
    0.11
    çļĦåij³éģĵ
    0.10
    åij³éģĵ
    0.10
     Taste
    0.10
    å°Ŀ
    0.10
    äºĨä¸Ģåı£
    0.10
    Activations Density 0.035%

    No Known Activations