© 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. 18573
    Prev
    Next
    INDEX
    Explanations

    expresses subjective qualities or states

    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
    å¿ĥ缮ä¸Ń
    -0.09
    imum
    -0.09
    etadata
    -0.09
    çĻ½èī²çļĦ
    -0.08
    åĢĶ
    -0.08
    éŨåīį
    -0.08
    Perm
    -0.08
    zik
    -0.08
    èĬĭ
    -0.08
    EMON
    -0.08
    POSITIVE LOGITS
    inning
    0.09
    è´´
    0.09
    èĵĵ
    0.08
    笼
    0.08
    é¼ĵèĪŀ
    0.08
    ä¸į失
    0.08
    èĻ
    0.07
    éĵ
    0.07
    å¾Ĺèµ·
    0.07
    æµģçķħ
    0.07
    Activations Density 0.078%

    No Known Activations