© 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. 5023
    Prev
    Next
    INDEX
    Explanations

    PDF, reports, system paths

    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
    ties
    -0.10
    说æ³ķ
    -0.09
    åĵij
    -0.09
    åѦåłĤ
    -0.09
    éħ¬
    -0.08
    ÑĦÑĤ
    -0.08
    ä¸Ģ个æĺŁæľŁ
    -0.08
    hti
    -0.08
    lings
    -0.08
    PLAIN
    -0.08
    POSITIVE LOGITS
    èĽ¾
    0.10
    ç³Ĭ
    0.10
    çīĿ
    0.09
    owitz
    0.09
    PRI
    0.09
    èı©æıIJ
    0.08
    ellas
    0.08
    uder
    0.08
    ìį¨
    0.08
    ÑģÑĤÑĢоен
    0.08
    Activations Density 0.004%

    No Known Activations