© 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. 19322
    Prev
    Next
    INDEX
    Explanations

    emphasis for truth

    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
     Hag
    -0.09
    CAP
    -0.09
    erior
    -0.08
    craft
    -0.08
    楸
    -0.08
    纷
    -0.08
    IDA
    -0.08
     cab
    -0.08
    .cap
    -0.07
     bi
    -0.07
    POSITIVE LOGITS
    çĭ¨
    0.09
    _LIB
    0.09
    æİĮ
    0.09
    天ä¸Ĭ
    0.09
    /license
    0.09
    è¢Ĵ
    0.09
    ITIES
    0.09
    alc
    0.08
    å¯Įæ°ij
    0.08
    Õ¹
    0.08
    Activations Density 0.086%

    No Known Activations