© 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. 54836
    Prev
    Next
    INDEX
    Explanations

    horizontal direction or arrangement

    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
    åŁ¤
    -0.10
    rious
    -0.10
    ingroup
    -0.09
    scape
    -0.09
    adir
    -0.09
    inic
    -0.09
    èIJ
    -0.08
    Breadcrumb
    -0.08
    esy
    -0.08
    .scalar
    -0.08
    POSITIVE LOGITS
    è§Ĥä¼Ĺ
    0.09
    ych
    0.09
    ãģ¾ãģ¾
    0.09
    éĺij
    0.09
    åī§
    0.09
    иÑĢÑĥ
    0.09
    姣
    0.08
     Levin
    0.08
    inz
    0.08
    æ¡£
    0.08
    Activations Density 0.046%

    No Known Activations