© 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. 36521
    Prev
    Next
    INDEX
    Explanations

    Wired, FT, Technology, MIT, Times

    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
    loo
    -0.10
    åıijå±ķ缮æłĩ
    -0.08
    akk
    -0.08
    å·¢
    -0.08
    é¹ľ
    -0.08
    磫
    -0.08
    pak
    -0.08
    orda
    -0.08
    ä¸Ģè§Ī
    -0.08
    aw
    -0.08
    POSITIVE LOGITS
    /MIT
    0.11
    èħ°
    0.09
    aption
    0.09
    lime
    0.09
    æݥ管
    0.08
    çIJĨåıij
    0.08
    èĽĶ
    0.08
    èĮĢ
    0.08
    appen
    0.08
    éĢģä¸Ĭ
    0.08
    Activations Density 0.021%

    No Known Activations