© 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. 57938
    Prev
    Next
    INDEX
    Explanations

    Joshua or names starting with ”jo”

    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
    istic
    -0.14
    itud
    -0.11
    ning
    -0.10
    ities
    -0.10
    -minded
    -0.10
    èIJ¥ä¸ļæī§çħ§
    -0.09
    oris
    -0.09
    strap
    -0.09
    ivia
    -0.09
    çĭIJ
    -0.09
    POSITIVE LOGITS
    æѤåĪ»
    0.10
    ye
    0.10
    æ´¸
    0.09
    ilt
    0.09
    .constraint
    0.09
    amel
    0.09
    ÑĥÑħ
    0.09
    ç¡®åĪĩ
    0.09
    害
    0.09
    管å§Ķä¼ļ
    0.08
    Activations Density 0.136%

    No Known Activations