© 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. 34262
    Prev
    Next
    INDEX
    Explanations

    body parts and internal states

    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
    ä»İä¸Ń
    -0.11
    åľ¨ä¸Ģèµ·
    -0.10
    ÑĢÑĭ
    -0.08
    è¿ĩæĿ¥
    -0.08
    éģİä¾Ĩ
    -0.08
    odyn
    -0.08
    (orig
    -0.08
    æĺĿ
    -0.08
    .orig
    -0.08
    _PARTITION
    -0.08
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.13
    èĶĵ
    0.10
    ä¸įè¿ľå¤Ħ
    0.10
    acher
    0.10
    åĴĮ社ä¼ļ
    0.09
    ä¸Ģè¾ĪåŃIJ
    0.09
    hone
    0.09
    á»Ī
    0.09
    å®ļäºĨ
    0.09
    çĤİ
    0.08
    Activations Density 0.076%

    No Known Activations