© 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. 55431
    Prev
    Next
    INDEX
    Explanations

    good followed by positive concepts

    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¢ĥçķĮ
    -0.10
    éĶĻè¿ĩ
    -0.09
    åľ¨è¿ĻéĩĮ
    -0.09
    fter
    -0.08
    å¹¼
    -0.08
    _uid
    -0.08
    missive
    -0.08
    qw
    -0.08
    OTH
    -0.08
    æĬļ
    -0.08
    POSITIVE LOGITS
    rok
    0.09
    åĿļæĮģ以
    0.08
    æľĭåıĭ们对
    0.08
    ĵį
    0.08
    éĶ¯
    0.08
    еÑģÑĮ
    0.08
    åı¯çĶ¨
    0.08
    举åĮĹ
    0.08
    空æ°Ķ
    0.08
    /provider
    0.08
    Activations Density 0.027%

    No Known Activations