© 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. 61749
    Prev
    Next
    INDEX
    Explanations

    appeal and effect

    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
     rein
    -0.09
    łģ
    -0.09
    _except
    -0.09
    Mutable
    -0.09
    untas
    -0.08
    lse
    -0.08
     Bale
    -0.08
    ä¹Ŀ大
    -0.08
    asu
    -0.08
    äºŃ
    -0.08
    POSITIVE LOGITS
     appeal
    0.13
     effect
    0.12
     Appeal
    0.11
     Effect
    0.10
    Effect
    0.10
    紧迫
    0.09
    æķĪåºĶ
    0.09
    宣
    0.09
    éĺ²èħIJ
    0.09
    -effect
    0.08
    Activations Density 0.067%

    No Known Activations