© 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. 22345
    Prev
    Next
    INDEX
    Explanations

    helical gearing, fluid seal, winding assemblies

    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
    æµħ
    -0.10
    æķ·
    -0.09
    æ¾Ħ
    -0.09
     двигаÑĤел
    -0.08
    è¡Įåĭķ
    -0.08
    é£Ł
    -0.08
    ยาà¸ĩ
    -0.08
    _ALWAYS
    -0.08
    undry
    -0.08
    çģ¾
    -0.08
    POSITIVE LOGITS
    hoc
    0.10
    à¸ī
    0.09
    éĹ´éļĻ
    0.09
    çĥĬ
    0.08
    åijĨ
    0.08
     Lama
    0.08
    缴æĴŃéĹ´
    0.08
    åݦ
    0.08
    罩
    0.08
    åĬ±
    0.08
    Activations Density 0.320%

    No Known Activations