© 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. 23302
    Prev
    Next
    INDEX
    Explanations

    into

    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
    åĪļ
    -0.09
    ä¸į便
    -0.09
    æ³Ħ
    -0.09
    éļIJéļIJ
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    è½»è½»åľ°
    -0.09
    婵
    -0.09
    åĨįè§ģ
    -0.09
     Ori
    -0.08
    å§Ĺ
    -0.08
    POSITIVE LOGITS
     into
    0.16
    into
    0.15
     Into
    0.14
    Into
    0.14
    _into
    0.14
     INTO
    0.12
     vÃło
    0.10
    .into
    0.10
    award
    0.10
    空çĻ½
    0.10
    Activations Density 0.090%

    No Known Activations