© 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. 23406
    Prev
    Next
    INDEX
    Explanations

    strange results or occurrences

    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
    een
    -0.11
    imum
    -0.10
    åī©
    -0.10
    eenth
    -0.09
    ìį¨
    -0.09
    ãģĦãģŁ
    -0.09
    æĢ»ä¹ĭ
    -0.09
    owed
    -0.09
     precious
    -0.09
    /trunk
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.12
     ÅŁeyler
    0.10
    -looking
    0.10
    ParameterValue
    0.10
    cko
    0.09
    illing
    0.09
    åĬŀäºĭå¤Ħ
    0.09
    usters
    0.09
    림
    0.09
    haft
    0.09
    Activations Density 0.005%

    No Known Activations