© 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. 21879
    Prev
    Next
    INDEX
    Explanations

    should be followed by verbs

    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
    assis
    -0.10
    å¾Ĺèµ·
    -0.10
    便æį·
    -0.08
    kat
    -0.08
     Hum
    -0.08
    elsen
    -0.08
    Hub
    -0.08
    amm
    -0.08
     Burton
    -0.08
    Keith
    -0.08
    POSITIVE LOGITS
    ardin
    0.11
    enor
    0.09
    å°¾
    0.09
     Jame
    0.09
    CharCode
    0.08
    GetInstance
    0.08
    	TokenName
    0.08
    注æĦı
    0.08
    huge
    0.08
    eldon
    0.08
    Activations Density 0.036%

    No Known Activations