© 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. 58247
    Prev
    Next
    INDEX
    Explanations

    move away, up, munch

    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
    æĿ¥çľĭçľĭ
    -0.12
     Lowe
    -0.10
    èµ°äºĨ
    -0.09
    æĿ¥çľĭ
    -0.09
    violent
    -0.09
    æŃ£ä¹ī
    -0.09
    pollo
    -0.08
    åĢŁåı£
    -0.08
    ittest
    -0.08
    大æłij
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.09
    otron
    0.09
    åĽº
    0.08
    ç°ĩ
    0.08
    夹
    0.08
     Sponsor
    0.08
    åĪ¶ä½ľ
    0.08
    åĽºçĦ¶
    0.08
    .cm
    0.07
    çģ¿çĥĤ
    0.07
    Activations Density 0.022%

    No Known Activations