© 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. 35639
    Prev
    Next
    INDEX
    Explanations

    affiliate links, compensation

    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
    æĬĸ
    -0.09
     paperback
    -0.08
    .break
    -0.08
    erer
    -0.08
    ãĤ«ãĥ©
    -0.08
    è°
    -0.08
     Archae
    -0.08
    arma
    -0.08
    Normalized
    -0.08
    æŶåĢĻ
    -0.08
    POSITIVE LOGITS
    itim
    0.10
    渲
    0.10
    æ¶Į
    0.09
    ABL
    0.09
    éĹªåħī
    0.09
     Blind
    0.09
    _PROF
    0.09
    chap
    0.09
    è¿Ļæī¹
    0.09
    éļĨéĩį
    0.09
    Activations Density 0.026%

    No Known Activations