© 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. 10307
    Prev
    Next
    INDEX
    Explanations

    Democratic Republic of the Congo

    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
    åĶĽ
    -0.09
    GBT
    -0.09
    oggle
    -0.09
    ugs
    -0.09
    æ´±
    -0.09
    ifax
    -0.08
    åŃ©
    -0.08
    oxel
    -0.08
    otland
    -0.08
     Gerr
    -0.08
    POSITIVE LOGITS
    æŁıæŀĹ
    0.09
    åı¤èĢģçļĦ
    0.09
     bark
    0.09
    ombo
    0.09
    å®īçĦ¶
    0.09
    RS
    0.08
    wan
    0.08
    è´¨åľ°
    0.08
    andel
    0.08
    MSN
    0.08
    Activations Density 0.017%

    No Known Activations