© 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. 52169
    Prev
    Next
    INDEX
    Explanations

    speech and language pathology

    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
    è°Ľ
    -0.10
    rael
    -0.10
     ê¶
    -0.10
    æĥ³æ³ķ
    -0.10
    ÑģÑĤолÑĮ
    -0.10
    è¾ľ
    -0.09
    ichi
    -0.09
    é¦ĸåħĪæĺ¯
    -0.09
     Kata
    -0.09
    éĵº
    -0.09
    POSITIVE LOGITS
    åıijéŁ³
    0.12
     Speech
    0.10
    åĸī
    0.10
    æĻ®éĢļè¯Ŀ
    0.10
    Speech
    0.10
    åĴ½åĸī
    0.10
    èħŃ
    0.10
    èĪĮ
    0.09
    onga
    0.09
    edy
    0.09
    Activations Density 0.081%

    No Known Activations