© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    following "with"

    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
    éĤij
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    bek
    -0.09
    çļĦçĶ»éĿ¢
    -0.09
     sided
    -0.08
    .MAIN
    -0.08
    æ¼
    -0.08
    oids
    -0.08
    Ñıем
    -0.08
    вой
    -0.08
    POSITIVE LOGITS
    åħ¶
    0.10
    èĩªå·±çļĦ
    0.10
    itel
    0.09
    亲æīĭ
    0.09
    çĪ·
    0.09
    æĹłæīĢ
    0.09
    bows
    0.08
     каж
    0.08
     suas
    0.08
    å®ĥçļĦ
    0.08
    Activations Density 0.056%

    No Known Activations