© 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. 57590
    Prev
    Next
    INDEX
    Explanations

    not followed by specific words

    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
    -panel
    -0.10
    çĹĶ
    -0.09
    utc
    -0.09
    辫
    -0.09
    åĥ»
    -0.09
    _IOCTL
    -0.09
    ende
    -0.09
    .tell
    -0.09
    çªģ
    -0.09
    çľĭä¸įåĪ°
    -0.09
    POSITIVE LOGITS
    åĬŁ
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
    åIJİæİĴ
    0.08
    ronic
    0.08
    .bs
    0.08
    ron
    0.07
    绵
    0.07
    .Not
    0.07
    æ·±å±Ĥ次
    0.07
    ort
    0.07
    Activations Density 0.035%

    No Known Activations