© 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. 18015
    Prev
    Next
    INDEX
    Explanations

    Han followed by various suffixes

    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
    ities
    -0.13
    sWith
    -0.11
    IRM
    -0.11
    è§ī
    -0.10
    osis
    -0.10
    ally
    -0.10
    ences
    -0.09
    auce
    -0.09
    ski
    -0.09
    idad
    -0.09
    POSITIVE LOGITS
    ubble
    0.09
    æĹĹä¸ĭ
    0.09
    OVER
    0.09
    forth
    0.09
    stro
    0.08
    zell
    0.08
    expo
    0.08
    oom
    0.08
    pole
    0.08
    ħ
    0.08
    Activations Density 0.015%

    No Known Activations