© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47741
    Prev
    Next
    INDEX
    Explanations

    can be, is a, has a

    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
    _GP
    -0.11
    IPA
    -0.09
    çĦķ
    -0.08
    VES
    -0.08
    enga
    -0.08
    _VF
    -0.08
    ç£Ĭ
    -0.08
     Trap
    -0.08
    ä¸ī级
    -0.08
    icho
    -0.08
    POSITIVE LOGITS
    ys
    0.09
    è´´å¿ĥ
    0.09
    åĭŁ
    0.08
    ç¯ĩ
    0.08
    íĴĢ
    0.08
     нап
    0.08
    åĩŃä»Ģä¹Ī
    0.08
    _ranges
    0.08
    RICT
    0.08
     landed
    0.07
    Activations Density 0.245%

    No Known Activations