© 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. 22224
    Prev
    Next
    INDEX
    Explanations

    electric followed by power, motor, arc, car, supplier

    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
    ãģ£ãģįãĤĬ
    -0.14
    chor
    -0.10
    ched
    -0.10
    apter
    -0.10
    леÑĤ
    -0.10
    enu
    -0.09
    à¹Ģà¸īà¸ŀาะ
    -0.09
    oms
    -0.09
    stead
    -0.09
    ont
    -0.08
    POSITIVE LOGITS
    ally
    0.20
    ALLY
    0.17
    -minded
    0.15
    mente
    0.13
     minded
    0.12
    ian
    0.11
    ELY
    0.11
    ITY
    0.11
    ity
    0.10
    ians
    0.10
    Activations Density 0.022%

    No Known Activations