© 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. 19809
    Prev
    Next
    INDEX
    Explanations

    whatever or whomever

    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
    aret
    -0.10
    çĿ¿
    -0.10
    ander
    -0.09
    æ°¸åĪ©
    -0.09
    mares
    -0.08
    rp
    -0.08
    ï¸ı
    -0.08
    åıijå±ķ壮大
    -0.08
    adera
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    POSITIVE LOGITS
    soever
    0.15
    ever
    0.12
    EVER
    0.12
    -ever
    0.11
     ever
    0.11
    à¹ĥà¸Ķ
    0.10
     any
    0.10
    ä»»ä½ķ
    0.10
     лÑİбой
    0.09
    æĹłè®º
    0.09
    Activations Density 0.036%

    No Known Activations