© 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. 19947
    Prev
    Next
    INDEX
    Explanations

    field of view

    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
    æĬ½
    -0.09
    åī¥
    -0.09
    éľŃ
    -0.09
    æ°´ä¸Ĭ
    -0.09
     ped
    -0.08
     tow
    -0.08
     mad
    -0.08
    çīĪæĿĥå½ĴåİŁ
    -0.08
    ick
    -0.08
     ty
    -0.08
    POSITIVE LOGITS
    ä»°
    0.11
    çĭŃçªĦ
    0.11
    лиÑĨ
    0.11
    çĭŃ
    0.10
    çĭ
    0.10
    è§Ĩéĩİ
    0.10
    æŃ»è§Ĵ
    0.10
    inges
    0.09
    çĶľèľľ
    0.09
    _async
    0.09
    Activations Density 0.220%

    No Known Activations