© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    period of time / moment / face / side

    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
    udit
    -0.10
    éªİ
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    LOY
    -0.09
    åĮĸåѦåĵģ
    -0.08
    çĽ¼æľĽ
    -0.08
    è¿Ļæł·æīįèĥ½
    -0.08
    ÑĦин
    -0.08
    _nl
    -0.08
    аÑĢаÑĤ
    -0.08
    POSITIVE LOGITS
    ady
    0.09
    æĮĸ
    0.08
    wich
    0.08
    ä»°
    0.08
    è¯Ŀ说
    0.08
    alin
    0.08
     Dig
    0.08
    bang
    0.08
    çħ§
    0.08
    aday
    0.08
    Activations Density 0.240%

    No Known Activations