© 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. 27574
    Prev
    Next
    INDEX
    Explanations

    B names

    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
    èĤ±
    -0.10
    è´¼
    -0.10
    éĵ¤
    -0.09
    åħīèį£
    -0.09
    åij¦
    -0.09
     наÑģÑĤоÑı
    -0.09
    cko
    -0.09
    æ³½
    -0.08
    çĤ¬
    -0.08
    afari
    -0.08
    POSITIVE LOGITS
    å°Ķ
    0.09
    妫
    0.09
    castle
    0.09
    haven
    0.09
    ä¸ĢçĤ¹
    0.09
    æĭĹ
    0.08
    æ¶Ĥ
    0.08
    ehr
    0.08
    destroy
    0.08
    计åħ¥
    0.08
    Activations Density 0.067%

    No Known Activations