© 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. 49326
    Prev
    Next
    INDEX
    Explanations

    status as or of

    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
    éĺī
    -0.09
    彧
    -0.08
    ÙĦÙĬÙĨ
    -0.08
     Tanks
    -0.08
    patibility
    -0.08
    ä¹Łåıªæľī
    -0.08
    .neo
    -0.08
     Fiat
    -0.08
    éģ¿åŃķ
    -0.08
    oppers
    -0.07
    POSITIVE LOGITS
    åľ°ä½į
    0.16
     quo
    0.15
     status
    0.11
    status
    0.11
    /status
    0.10
    çļĦåľ°ä½į
    0.10
     Status
    0.10
     Protected
    0.10
    (status
    0.10
    STATUS
    0.10
    Activations Density 0.039%

    No Known Activations