© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10578
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    ishly
    -0.10
    ÑĪки
    -0.10
    theless
    -0.09
    iban
    -0.09
    bens
    -0.09
    ê¹IJ
    -0.09
    igu
    -0.09
    nier
    -0.09
    ï¬Ħ
    -0.09
    gether
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.10
    aniel
    0.10
    ëģĶ
    0.09
    ness
    0.09
    纬
    0.09
    ools
    0.09
    İ·
    0.09
    æī¾åĽŀ
    0.08
    gers
    0.08
     mor
    0.08
    Activations Density 0.069%

    No Known Activations