© 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. 9219
    Prev
    Next
    INDEX
    Explanations

    urls or domains

    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
    1
    -0.10
    çīµ
    -0.09
    2
    -0.09
     I
    -0.09
    7
    -0.09
    8
    -0.08
    9
    -0.08
    els
    -0.08
    3
    -0.08
    åıªæĺ¯
    -0.08
    POSITIVE LOGITS
    èģĶç³»æĪij们
    0.10
    /contact
    0.10
    <quote
    0.10
    åıijè¨Ģ人
    0.10
    CONTACT
    0.10
    廪
    0.09
    _TRANSL
    0.09
     roÅĽ
    0.09
    TEGR
    0.09
    è·ĥ
    0.09
    Activations Density 0.080%

    No Known Activations