© 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. 33088
    Prev
    Next
    INDEX
    Explanations

    "The" followed by sequences or names

    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
    鸨
    -0.08
    _SIGNATURE
    -0.08
    çijĽ
    -0.08
    驾
    -0.07
     Suz
    -0.07
    onal
    -0.07
     Ung
    -0.07
    пÑĥÑĤ
    -0.07
    othermal
    -0.07
    бÑĥ
    -0.07
    POSITIVE LOGITS
    æ¼¾
    0.10
    å¼Ħå¾Ĺ
    0.10
    _EDEFAULT
    0.09
    ä¸Ńæłĩ
    0.09
    icensed
    0.09
    æĥ§
    0.09
    iquement
    0.09
    PubMed
    0.08
    icus
    0.08
    malink
    0.08
    Activations Density 0.337%

    No Known Activations