© 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. 33444
    Prev
    Next
    INDEX
    Explanations

    baseline determination or condition

    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
    èĥĮéĿ¢
    -0.09
    åľ°çĤ¹
    -0.09
    arium
    -0.09
    åĢ¾
    -0.08
    ç½ijç«Ļåľ°åĽ¾
    -0.08
    åŁ¼
    -0.08
    æ¦ľé¦ĸ
    -0.08
    ç¼ĿéļĻ
    -0.08
    _GU
    -0.08
    åĬĽåѦ
    -0.08
    POSITIVE LOGITS
     baseline
    0.20
    baseline
    0.19
    常æĢģ
    0.18
    Baseline
    0.18
    åŁºåĩĨ
    0.15
    _baseline
    0.13
    常æĢģåĮĸ
    0.13
    aseline
    0.13
     Establishment
    0.12
    æŃ£å¸¸
    0.11
    Activations Density 0.216%

    No Known Activations