© 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. 32550
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    NESS
    -0.09
    ย
    -0.09
    稿
    -0.09
    اÙħÙĦ
    -0.09
    _except
    -0.08
    getti
    -0.08
     Petro
    -0.08
    lijke
    -0.08
    å¹ħ
    -0.08
    agi
    -0.08
    POSITIVE LOGITS
    ëģĶ
    0.10
    engo
    0.10
    nip
    0.09
    åĩºå¤Ħ
    0.09
    ience
    0.09
    ãģĻãģIJãģ«
    0.09
    éĺį
    0.09
    ius
    0.09
    ãģ¯ãģĺ
    0.09
    ãģ£ãģĵ
    0.09
    Activations Density 0.086%

    No Known Activations