© 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. 32459
    Prev
    Next
    INDEX
    Explanations

    paste and related word endings

    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
     rum
    -0.09
    athers
    -0.09
    IZER
    -0.09
    rum
    -0.08
    nings
    -0.08
    çĿ¬
    -0.08
     nuisance
    -0.08
    æķĪæŀľåĽ¾
    -0.08
    nte
    -0.08
     Associates
    -0.08
    POSITIVE LOGITS
    board
    0.11
    ural
    0.10
    ðŁı»
    0.10
    ç³Ĭæ¶Ĥ
    0.10
    ulation
    0.09
    å®Ľ
    0.09
    åĵ¥
    0.09
    flow
    0.09
    igue
    0.09
    engers
    0.09
    Activations Density 0.011%

    No Known Activations