© 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. 52881
    Prev
    Next
    INDEX
    Explanations

    admire or admiral

    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
    mates
    -0.12
    mate
    -0.11
    ting
    -0.10
    ëģĶ
    -0.09
    ters
    -0.09
    ipt
    -0.09
    opp
    -0.09
    away
    -0.09
    ед
    -0.08
    ed
    -0.08
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.12
    auce
    0.10
    é¦Ķ
    0.10
    icable
    0.10
    ably
    0.10
    otos
    0.10
    ç®Ģ约
    0.09
     اÙĦØ®ÙĦ
    0.09
    ãģĤãģ®
    0.09
    CDATA
    0.09
    Activations Density 0.004%

    No Known Activations