© 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. 34139
    Prev
    Next
    INDEX
    Explanations

    filming, filming, filming, taped, taped, shooting, photography

    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
    lander
    -0.11
    ëıĮ
    -0.09
    umerator
    -0.09
    èIJ¥åķĨ
    -0.09
    tone
    -0.09
    lijke
    -0.09
    ä¹Łä¸įæķ¢
    -0.09
    ively
    -0.09
    rame
    -0.08
    ioned
    -0.08
    POSITIVE LOGITS
    ites
    0.10
    çķ´
    0.09
    utes
    0.09
    arine
    0.09
    çĶµè§Ĩ
    0.09
    åīĬ
    0.08
    éŃģ
    0.08
    è¡ĮæĺŁ
    0.08
    ille
    0.08
    arf
    0.08
    Activations Density 0.012%

    No Known Activations