© 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. 37614
    Prev
    Next
    INDEX
    Explanations

    manual and electric operation

    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
    è¦ģéĹ»
    -0.10
    éĺµ
    -0.10
    åİŃ
    -0.09
    é»ı
    -0.09
    nox
    -0.09
    alez
    -0.09
    çĶŁæĢķ
    -0.09
    çĹ´
    -0.09
    æĻ°
    -0.09
    oodles
    -0.09
    POSITIVE LOGITS
    人åĬĽ
    0.10
    æľīæľŁ
    0.10
    Manual
    0.09
    å¾Ĵ
    0.09
    ÑĤÑıж
    0.09
    RET
    0.09
    .walk
    0.08
     manual
    0.08
     manually
    0.08
    reta
    0.08
    Activations Density 0.235%

    No Known Activations