© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    sham or cham

    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
    vice
    -0.10
    ivity
    -0.10
    urator
    -0.09
    ularity
    -0.09
    æºĸ
    -0.09
    prises
    -0.09
    erval
    -0.09
    -know
    -0.09
    andon
    -0.09
    ction
    -0.09
    POSITIVE LOGITS
    istic
    0.11
    éĢ¢
    0.09
    åĩĽ
    0.09
    èĸĩ
    0.09
    lessly
    0.08
    fully
    0.08
    ÑĢаÐ
    0.08
    aska
    0.08
    itas
    0.08
    èij±
    0.08
    Activations Density 0.005%

    No Known Activations