© 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. 30920
    Prev
    Next
    INDEX
    Explanations

    conditions are met:

    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
    iston
    -0.11
    ettes
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    unto
    -0.09
    ģ
    -0.09
    cip
    -0.09
    ment
    -0.09
    atra
    -0.09
    ìĽĥ
    -0.08
    å¹ħ
    -0.08
    POSITIVE LOGITS
    ters
    0.16
    ting
    0.14
    TING
    0.13
    ropolis
    0.13
    tern
    0.13
    tle
    0.12
    ioned
    0.12
    rix
    0.11
    ë¥ł
    0.11
    Ùij
    0.11
    Activations Density 0.036%

    No Known Activations