© 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. 31851
    Prev
    Next
    INDEX
    Explanations

    do you/I questions

    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
    大è±Ĩ
    -0.09
    çĻ½éĵ¶
    -0.08
    zin
    -0.08
    åıªè¦ģæĺ¯
    -0.08
    nds
    -0.08
     Gad
    -0.08
    ç²®é£Ł
    -0.08
    amat
    -0.08
    quam
    -0.08
    ç²ĺ
    -0.08
    POSITIVE LOGITS
    ç¡®ä¿Ŀ
    0.11
     garant
    0.10
    çŁ¥éģĵ
    0.09
    æ·¹
    0.09
    çŁ¥éģĵèĩªå·±
    0.09
    itzer
    0.09
    ä¿Ŀè¯ģ
    0.08
    WithMany
    0.08
    çľĭå¾ħ
    0.08
     infl
    0.08
    Activations Density 0.040%

    No Known Activations