© 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. 36531
    Prev
    Next
    INDEX
    Explanations

    human rights

    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
    nable
    -0.09
    åĨ³
    -0.08
    Hugh
    -0.08
    ä¼Ļ
    -0.08
    -appointed
    -0.08
    空æ°ĶåĩĢåĮĸ
    -0.08
    ÑĤÑĮ
    -0.08
    çªł
    -0.08
    çĥ
    -0.08
    laÅŁ
    -0.07
    POSITIVE LOGITS
    istic
    0.09
    èĪŁ
    0.09
    èį¯ä¸ļ
    0.09
    ABCDEFGHI
    0.09
    è¿ĻæĿ¡
    0.09
    èĩªçĦ¶æĺ¯
    0.09
    iod
    0.09
    驺
    0.09
    éĤĪ
    0.08
    ENSION
    0.08
    Activations Density 0.019%

    No Known Activations