© 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. 35078
    Prev
    Next
    INDEX
    Explanations

    Pin

    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
    ening
    -0.12
    ened
    -0.10
    æ±Ĺæ°´
    -0.10
    sic
    -0.10
    ฯ
    -0.09
    åħļå§Ķ
    -0.09
    anson
    -0.09
    ãģªãĤĭ
    -0.09
    媳
    -0.09
    çĽijäºĭä¼ļ
    -0.09
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.11
    lify
    0.11
    å®ļäºĨ
    0.10
    -ups
    0.10
    ixe
    0.10
    亥
    0.09
    ning
    0.09
    æ³
    0.09
    labs
    0.09
    ges
    0.09
    Activations Density 0.026%

    No Known Activations