© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36031
    Prev
    Next
    INDEX
    Explanations

    person's nationality

    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
     trivial
    -0.08
    alon
    -0.08
    éĩįç£ħ
    -0.08
    ấy
    -0.08
    éĢł
    -0.07
     gover
    -0.07
    èį¡
    -0.07
    踽
    -0.07
    éĶ²
    -0.07
    dash
    -0.07
    POSITIVE LOGITS
    çĶŁäºİ
    0.12
    åĩºçĶŁäºİ
    0.11
    æįįåį«
    0.10
    æ¯ķä¸ļäºİ
    0.10
    çĭĻåĩ»
    0.09
     добÑĢо
    0.09
    ä¿¡æģ¯åħ¬å¼Ģ
    0.09
    LIK
    0.09
    _Module
    0.09
    ÑģÑĤÑĥпил
    0.09
    Activations Density 0.208%

    No Known Activations