© 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. 27321
    Prev
    Next
    INDEX
    Explanations

    intelligence and cognitive ability scales

    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
    稿件
    -0.11
    AMPL
    -0.10
    稿
    -0.09
    çĪ»
    -0.09
    åĩ¹
    -0.09
     shoulder
    -0.09
    arian
    -0.09
    ampling
    -0.09
    веÑģ
    -0.09
    æ¯ĽåŃĶ
    -0.08
    POSITIVE LOGITS
    æĻºåķĨ
    0.18
    æĻºåĬĽ
    0.18
    IQ
    0.15
     IQ
    0.14
    intelligence
    0.11
     intelligence
    0.11
     iq
    0.11
    è®°å¿ĨåĬĽ
    0.11
     Intelligence
    0.10
     Mens
    0.10
    Activations Density 0.174%

    No Known Activations