© 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. 34358
    Prev
    Next
    INDEX
    Explanations

    land and water

    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
    ç²ī
    -0.11
    èıĺ
    -0.09
    çĸ½
    -0.09
    ç»°
    -0.09
    ä¿Ŀå®ī
    -0.09
    æ¯Ĥ
    -0.09
     coun
    -0.09
    amina
    -0.08
    毡
    -0.08
    acon
    -0.08
    POSITIVE LOGITS
    æµ·æ´ĭ
    0.14
    è¿ľæ´ĭ
    0.13
     oceans
    0.13
    æ°´åŁŁ
    0.13
    æµ·
    0.13
     sea
    0.12
    èĮ«èĮ«
    0.12
     ocean
    0.11
    æ·±å¤Ħ
    0.11
    èĪŁ
    0.11
    Activations Density 0.102%

    No Known Activations