© 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. 62979
    Prev
    Next
    INDEX
    Explanations

    first with qualifier

    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
    两åı¥
    -0.11
    lest
    -0.11
    åIJ«
    -0.10
    å¯Įæľī
    -0.10
    etheless
    -0.10
    bracht
    -0.10
    GEST
    -0.09
    ì°©
    -0.09
    èıĬ
    -0.09
    è¿ŀéĶģ
    -0.09
    POSITIVE LOGITS
    sing
    0.09
    -level
    0.09
     Zu
    0.08
    ron
    0.08
    er
    0.08
    åĬ¨çī©åĽŃ
    0.08
    mat
    0.07
    å¿įåıĹ
    0.07
    sy
    0.07
    ä¸ĸçķĮçļĦ
    0.07
    Activations Density 0.055%

    No Known Activations