© 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. 56180
    Prev
    Next
    INDEX
    Explanations

    Gerry

    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
    inate
    -0.08
    ä¸Ńè¶ħ
    -0.08
    ina
    -0.08
    emaker
    -0.08
    inas
    -0.08
    uffer
    -0.08
    è£Ķ
    -0.08
    åݨå¸Ī
    -0.08
    åģ¥åº·åıijå±ķ
    -0.08
    uras
    -0.08
    POSITIVE LOGITS
    loyd
    0.09
    åĨįå¤ļ
    0.09
    çĭ¸
    0.09
    æĪijçľĭ
    0.09
    è¿Ļå¥Ĺ
    0.09
    bery
    0.08
    å¯ĦãģĽ
    0.08
    æ²
    0.08
    otten
    0.08
    elled
    0.08
    Activations Density 0.002%

    No Known Activations