© 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. 57434
    Prev
    Next
    INDEX
    Explanations

    positive qualities for growth

    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
    боÑĢ
    -0.10
    å®ļäºĨ
    -0.09
    osoph
    -0.08
    éħ·
    -0.08
    ãĤ
    -0.08
     Bali
    -0.08
    po
    -0.08
    æ²¥
    -0.08
    åĬŀ
    -0.08
    PARSE
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    NESS
    0.12
    liness
    0.10
    _latency
    0.10
    heit
    0.09
    å¾ķ
    0.09
     Civ
    0.09
    çķļ
    0.09
    nemonic
    0.09
    nist
    0.09
    Activations Density 0.006%

    No Known Activations