© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    keen observations and insight

    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
    åĬ³
    -0.11
    溯
    -0.08
    åij¼
    -0.08
    igor
    -0.08
    è¯¥æł¡
    -0.08
    esto
    -0.08
    elda
    -0.08
    yd
    -0.07
     Sab
    -0.07
     Labor
    -0.07
    POSITIVE LOGITS
    æķıéĶIJ
    0.19
    æ´ŀå¯Ł
    0.17
    è§Ĥå¯Ł
    0.14
    æįķæįī
    0.14
    è§Ģå¯Ł
    0.13
    çĬĢ
    0.13
    æķıæĦŁ
    0.12
    æħ§
    0.12
     observation
    0.11
    .obs
    0.11
    Activations Density 0.029%

    No Known Activations