© 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. 20190
    Prev
    Next
    INDEX
    Explanations

    we'll deliver, will be

    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
    å¤Ħäºİ
    -0.09
    çĶ°éĩİ
    -0.09
    çĶ©
    -0.09
    对èĩªå·±çļĦ
    -0.08
    rimp
    -0.08
    享
    -0.08
    éĢĤåIJĪèĩªå·±
    -0.08
    æĭĪ
    -0.08
    eration
    -0.08
    caret
    -0.08
    POSITIVE LOGITS
    æıIJä¾Ľ
    0.14
    å¸®ä½ł
    0.13
    亲èĩª
    0.11
    æıIJä¾ĽçļĦ
    0.11
     provide
    0.10
     ìłľê³µ
    0.10
     provided
    0.10
    éĢĢè¿ĺ
    0.10
    åıªè¦ģä½ł
    0.10
    _GU
    0.10
    Activations Density 0.077%

    No Known Activations