© 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. 20004
    Prev
    Next
    INDEX
    Explanations

    goals, titles, year, season, career

    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
    çī¹æ´¾
    -0.12
    éĺĶ
    -0.10
    SKIP
    -0.09
    åĹ¡
    -0.09
    è¹Ĵ
    -0.08
    à¸ŀล
    -0.08
    è¿ħéĢŁ
    -0.08
     sortie
    -0.08
    AIT
    -0.08
    Ñħодим
    -0.08
    POSITIVE LOGITS
    ä¹ŁæĽ¾
    0.09
    ä¼ĺå¼Ĥ
    0.09
    kus
    0.09
    缮çĿ¹
    0.08
    è®°è½½
    0.08
    ä»İå°ıå°±
    0.08
    åľ¨çĶŁæ´»ä¸Ń
    0.08
    积累
    0.08
    çĨı
    0.08
    erve
    0.08
    Activations Density 0.072%

    No Known Activations