© 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. 48515
    Prev
    Next
    INDEX
    Explanations

    denying allegations or accusations

    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
     ÑĢазв
    -0.09
    (tol
    -0.09
     вне
    -0.09
    olan
    -0.08
    ìķħ
    -0.08
    åij£
    -0.08
    vince
    -0.08
    ButtonItem
    -0.08
    ино
    -0.08
    æĮijåīĶ
    -0.08
    POSITIVE LOGITS
     ever
    0.10
    è°Ł
    0.09
    ä¸ĢåĪĩ
    0.09
    èĻ¬
    0.09
    为ä»Ģä¹Īä¸į
    0.09
    ãģ¯ãģĺãĤģ
    0.09
    å±¥
    0.08
     being
    0.08
    çĻĸ
    0.08
    anc
    0.08
    Activations Density 0.013%

    No Known Activations