© 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. 56026
    Prev
    Next
    INDEX
    Explanations

    electronic devices, brands, or specific product names

    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
    xis
    -0.09
    åİķ
    -0.09
    lama
    -0.09
    åĸ§
    -0.09
    å¿«æīĭ
    -0.08
    arov
    -0.08
    ete
    -0.08
    èĬ±å¼Ģ
    -0.08
    uran
    -0.08
    åıijå±ķæĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    èĤ¡æľ¬
    0.09
    çĤ³
    0.09
    .norm
    0.09
    æµģ浪
    0.08
    å¢ŀèĩ³
    0.08
    ä¸Ńä»ĭæľºæŀĦ
    0.08
    å¸ĤåľºèIJ¥éĶĢ
    0.08
    /exec
    0.08
    æĢ§åĪ«
    0.08
    ä¸Ģä¸Ģ
    0.08
    Activations Density 0.005%

    No Known Activations