© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    wireless connection or remote control

    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
    æħİéĩį
    -0.09
    _IA
    -0.09
     fiat
    -0.09
    _pid
    -0.09
    PID
    -0.08
    积
    -0.08
    çļĦåħ´è¶£
    -0.08
    绺
    -0.08
    Pizza
    -0.08
     bub
    -0.08
    POSITIVE LOGITS
    庾
    0.11
    .ping
    0.10
    åįĥéĩĮ
    0.10
    -links
    0.09
    çķľ
    0.09
     Grip
    0.09
    诱人
    0.09
    osti
    0.09
    è·ĿéĽ¢
    0.09
    erable
    0.09
    Activations Density 0.148%

    No Known Activations