© 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. 9814
    Prev
    Next
    INDEX
    Explanations

    barney, BBQ, GoDaddy

    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
    éĶ¥
    -0.10
    .struct
    -0.09
    STALL
    -0.09
    NSObject
    -0.09
    loser
    -0.09
    iless
    -0.09
    æį©
    -0.09
    âĩĦ
    -0.09
    ê¶Į
    -0.09
    FLOW
    -0.09
    POSITIVE LOGITS
    çĥĺå¹²
    0.09
    eln
    0.09
    çĤĬ
    0.08
    2
    0.08
    è¾Ķ
    0.08
    æĿ¥å®¾
    0.08
    ç¼°
    0.08
    0.08
    æĶ¾åĩº
    0.08
    EXT
    0.08
    Activations Density 0.001%

    No Known Activations