© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22078
    Prev
    Next
    INDEX
    Explanations

    See docs

    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
    åĵªæĢķ
    -0.10
     Regards
    -0.10
    .Modules
    -0.08
     Kling
    -0.08
    ilst
    -0.08
    åŀĤ
    -0.08
    AREN
    -0.08
    çģ«çĦ°
    -0.08
    _expired
    -0.08
     Morg
    -0.08
    POSITIVE LOGITS
    ä½ļ
    0.11
    çŃł
    0.09
    åijĬ
    0.09
    åıĸåĨ³
    0.09
    imos
    0.08
    ä»ĭ
    0.08
    çIJĽ
    0.08
     Sne
    0.08
    éļıæŶ
    0.08
    ä¸įç¡®å®ļ
    0.08
    Activations Density 0.264%

    No Known Activations