© 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. 55639
    Prev
    Next
    INDEX
    Explanations

    faster, simpler, more compact

    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
    æĽ´ä½ķåĨµ
    -0.09
    atitude
    -0.09
    åįģ大
    -0.08
    inas
    -0.08
    wt
    -0.08
    å°±å¤Ł
    -0.08
    楼主
    -0.08
    reinterpret
    -0.08
    çİ°è¡Į
    -0.08
    .trace
    -0.08
    POSITIVE LOGITS
    çļĦä¼ĺçĤ¹
    0.16
    ä¼ĺçĤ¹
    0.13
    çļĦ好å¤Ħ
    0.12
    缺çĤ¹
    0.12
    è¾ĥå°ij
    0.12
    éĢĤçĶ¨äºİ
    0.12
    è¾ĥ为
    0.11
    è¾ĥå¿«
    0.11
    éĢĤåIJĪ
    0.11
    æĢ§ä»·
    0.10
    Activations Density 0.272%

    No Known Activations