© 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. 49878
    Prev
    Next
    INDEX
    Explanations

    appointments and job titles

    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
    æĥ³å¿ħ
    -0.09
    åĬ©
    -0.09
    å¤ļæķ°
    -0.08
    缸åºĶ
    -0.08
     Ñĥзн
    -0.08
    å°½éĩı
    -0.08
    æĶ¶
    -0.08
    å¹³æĿ¿
    -0.08
    _unused
    -0.08
    ç®Ģ称
    -0.08
    POSITIVE LOGITS
    éĶĢæ¯ģ
    0.08
     proverb
    0.08
    åīįè¡Į
    0.08
    åĬ«
    0.08
    .au
    0.08
    rema
    0.08
     Fres
    0.08
     cắt
    0.08
    æ£Ģçĸ«
    0.08
    æ¡¢
    0.08
    Activations Density 0.824%

    No Known Activations