© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37451
    Prev
    Next
    INDEX
    Explanations

    your lifestyle or needs

    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
    Validity
    -0.09
    Rgb
    -0.09
    èĩ¾
    -0.09
     гÑĢ
    -0.09
    æ¦ľ
    -0.09
    elseif
    -0.08
     Julian
    -0.08
     bek
    -0.08
    ksi
    -0.08
    ugen
    -0.08
    POSITIVE LOGITS
    çī¹çĤ¹
    0.16
    å®ŀéĻħæĥħåĨµ
    0.15
    éľĢæ±Ĥ
    0.13
    çļĦéľĢæ±Ĥ
    0.13
    åĽ½æĥħ
    0.13
    客æĪ·éľĢæ±Ĥ
    0.12
     realities
    0.12
     needs
    0.12
    åħ·ä½ĵæĥħåĨµ
    0.12
    çī¹çĤ¹æĺ¯
    0.12
    Activations Density 0.140%

    No Known Activations