© 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. 11441
    Prev
    Next
    INDEX
    Explanations

    Pitchfork slapped or iff mail

    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
     Bail
    -0.09
    åħħåĪĨ
    -0.09
    iego
    -0.09
    ogi
    -0.09
    ogy
    -0.09
    ÑģÑĤв
    -0.08
    åĬłæ²¹
    -0.08
    åĦĢ
    -0.08
    æ³Ĭ
    -0.08
    åħħ
    -0.08
    POSITIVE LOGITS
    å«¡
    0.10
    对æĬĹ
    0.09
    çļĦå½±åĵį
    0.09
    åŀĦ
    0.09
     Lawson
    0.08
    人å±ħçݯå¢ĥ
    0.08
    æĦĪåıij
    0.08
    argent
    0.08
    pace
    0.08
    æ³°
    0.08
    Activations Density 0.007%

    No Known Activations