© 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. 37781
    Prev
    Next
    INDEX
    Explanations

    logic and reasoning

    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
    åģļçļĦäºĭæĥħ
    -0.10
    åģļçļĦäºĭ
    -0.10
    éĶ¦
    -0.10
    _rights
    -0.09
    æŀ¶
    -0.08
    å¨ģåIJį
    -0.08
    æ·±æ·±åľ°
    -0.08
    nts
    -0.08
    uther
    -0.08
    nist
    -0.08
    POSITIVE LOGITS
    éĢ»è¾ij
    0.16
     reasoning
    0.14
     logic
    0.14
     Logic
    0.12
    logic
    0.12
     rationale
    0.11
    éĤ
    0.11
    çIJĨçĶ±
    0.11
    _logic
    0.10
    Logic
    0.10
    Activations Density 0.031%

    No Known Activations