© 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. 1599
    Prev
    Next
    INDEX
    Explanations

    he following a he

    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
    æĪĸå¤ļ
    -0.09
    PRINTF
    -0.09
    å¾ħ
    -0.09
    ader
    -0.08
    layer
    -0.08
    ra
    -0.08
    plemented
    -0.08
    ues
    -0.08
    饶
    -0.08
    nam
    -0.08
    POSITIVE LOGITS
    NSE
    0.10
    aving
    0.10
    wig
    0.10
    brew
    0.09
    忱
    0.09
    zier
    0.09
    á¹ħ
    0.09
    Listen
    0.09
    ugen
    0.08
    åij
    0.08
    Activations Density 0.033%

    No Known Activations