© 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. 56208
    Prev
    Next
    INDEX
    Explanations

    try to or endeavour to

    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
    éĴ
    -0.09
    çģ¼
    -0.09
     nét
    -0.08
    irie
    -0.08
    uras
    -0.08
    rapid
    -0.08
    æī£
    -0.08
    ura
    -0.08
    erten
    -0.08
     khuôn
    -0.07
    POSITIVE LOGITS
    å°½éĩı
    0.18
    åĬªåĬĽ
    0.17
    å°½åĬĽ
    0.15
    åĬĽæ±Ĥ
    0.15
     effort
    0.14
    çļĦåĬªåĬĽ
    0.14
    å°Ŀè¯ķ
    0.13
     strive
    0.13
    äºīåıĸ
    0.13
     striving
    0.12
    Activations Density 0.051%

    No Known Activations