© 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. 58586
    Prev
    Next
    INDEX
    Explanations

    carcinoma

    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
    oux
    -0.10
    icken
    -0.09
     Beg
    -0.08
    ORIES
    -0.08
    -slide
    -0.08
    ä½İæĪIJæľ¬
    -0.08
     jose
    -0.08
    orrh
    -0.08
    æĸ°éĹ»ç½ij
    -0.08
    çļĦ人çī©
    -0.08
    POSITIVE LOGITS
    è¡£
    0.09
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.09
    çīŁ
    0.08
    çļ¤
    0.08
    _NM
    0.08
    linger
    0.08
    _packet
    0.08
    å®īåħ¨ç®¡çIJĨ
    0.08
    èħĶ
    0.08
    .setAuto
    0.08
    Activations Density 0.003%

    No Known Activations