© 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. 22563
    Prev
    Next
    INDEX
    Explanations

    key to success/procedure/future

    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
    ations
    -0.10
    涯
    -0.09
    noc
    -0.08
     McCart
    -0.08
    essor
    -0.08
    éªĬ
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    楼主
    -0.08
    ation
    -0.08
    icine
    -0.08
    POSITIVE LOGITS
    hole
    0.15
    cloak
    0.12
    frames
    0.11
    lessly
    0.10
    holes
    0.10
    ermann
    0.10
    人çī©
    0.09
    antor
    0.09
    读æĩĤ
    0.09
    ðŁĶij
    0.09
    Activations Density 0.040%

    No Known Activations