© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    car insurance

    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
    æ²IJæµ´
    -0.10
    pedia
    -0.09
    undy
    -0.09
    衾
    -0.09
    ç§ijæĻ®
    -0.09
    èľ¡
    -0.08
     /*----------------------------------------------------------------
    -0.08
    åĨ·åĨ·
    -0.08
    åĬŁè¯¾
    -0.08
    agma
    -0.08
    POSITIVE LOGITS
    .snapshot
    0.10
    åĴĢ
    0.09
    驾
    0.09
    _iff
    0.09
    éĺ²çĽĹ
    0.08
    é¼¹
    0.08
    Å¡t
    0.08
    ç»Ń
    0.08
    åijĻ
    0.08
    trag
    0.08
    Activations Density 0.044%

    No Known Activations