© 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. 11455
    Prev
    Next
    INDEX
    Explanations

    youth related topics

    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
    ritz
    -0.10
    åĮ»ç§ij大åѦ
    -0.10
    Unnamed
    -0.10
    å¼ķãģį
    -0.10
     ÑģлÑĥÑĩаÑı
    -0.10
    ä½Ĩä¸įéĻIJ
    -0.09
    åıĶåıĶ
    -0.09
    OrUpdate
    -0.09
    åİļåİļ
    -0.09
    å§ĭç»ĪåĿļæĮģ
    -0.09
    POSITIVE LOGITS
    fulness
    0.13
    fully
    0.11
    ful
    0.10
    FUL
    0.10
    ields
    0.10
    quake
    0.10
    ishly
    0.09
    ield
    0.09
    blood
    0.09
    ward
    0.09
    Activations Density 0.018%

    No Known Activations