© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    bare minimum or bones

    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
    emia
    -0.11
    å´ĩ
    -0.10
    emi
    -0.10
    å°º
    -0.09
    çĦ¦
    -0.09
    tat
    -0.09
    anos
    -0.09
    eler
    -0.08
    elen
    -0.08
    andan
    -0.08
    POSITIVE LOGITS
    裸
    0.13
    bare
    0.12
    -hearted
    0.10
     Bare
    0.10
    _minimum
    0.10
    uner
    0.09
    è®°å¾Ĺ
    0.09
    xes
    0.09
    stå
    0.09
    轩è¾ķ
    0.09
    Activations Density 0.008%

    No Known Activations