© 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. 18829
    Prev
    Next
    INDEX
    Explanations

    question and answer

    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
     behold
    -0.09
    ä¸Ģç¢Ĺ
    -0.08
    çļĦ表çİ°
    -0.08
    ToWorld
    -0.08
    irmed
    -0.08
    igator
    -0.08
    دÙĦ
    -0.08
    _xor
    -0.08
    夥
    -0.08
    UTOR
    -0.08
    POSITIVE LOGITS
    对æĸ¹
    0.10
    elic
    0.09
    çľ¼åīįçļĦ
    0.09
     налиÑĩ
    0.09
    å£ij
    0.09
    éķ¿è¾¾
    0.09
    ::__
    0.08
    æĸ°æĺ¥
    0.08
    åı°é£İ
    0.08
    éĻĨ
    0.08
    Activations Density 0.014%

    No Known Activations