© 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. 52855
    Prev
    Next
    INDEX
    Explanations

    says / tells / tell / said

    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
    ä¼ŀ
    -0.12
    æķŀ
    -0.10
    oola
    -0.09
    çĽ¸äº²
    -0.09
    åĮĻ
    -0.09
    ноÑģÑĤей
    -0.08
    æĿĢ人
    -0.08
    -dat
    -0.08
    ï¸
    -0.08
    urred
    -0.08
    POSITIVE LOGITS
    åIJįçīĩ
    0.10
    MAND
    0.10
    ÅĤu
    0.09
    hey
    0.09
    ä½ķå¿ħ
    0.09
    _tol
    0.09
    æ³Ľ
    0.09
    ãģ©ãĤĵãģ©
    0.09
    æĨĶ
    0.09
     Tell
    0.09
    Activations Density 0.033%

    No Known Activations