© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    Connor, MacMullen, Leighton

    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
    æĸ°åŁİ
    -0.11
    vig
    -0.09
    ãĤ¬ãĤ¤
    -0.09
    sse
    -0.09
    asmus
    -0.09
    lein
    -0.08
    etas
    -0.08
    issan
    -0.08
    sst
    -0.08
    寸
    -0.08
    POSITIVE LOGITS
    COPE
    0.10
    潤
    0.08
    æ¼±
    0.08
    çĪ¬
    0.08
    峡谷
    0.08
    Ñİ
    0.08
    razil
    0.08
    æijĺç¼ĸ
    0.08
    èij³
    0.08
    æĭ±
    0.08
    Activations Density 0.211%

    No Known Activations