© 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. 9902
    Prev
    Next
    INDEX
    Explanations

    turn into, turn out, turn up

    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
     hers
    -0.11
    hợ
    -0.09
    зам
    -0.09
    esda
    -0.09
    _DIRS
    -0.09
    permanent
    -0.09
    åīij
    -0.09
    çĻ¾èĬ±
    -0.09
    åħ»
    -0.09
    Permanent
    -0.09
    POSITIVE LOGITS
    ke
    0.10
    se
    0.09
    åľ°çIJĥä¸Ĭ
    0.08
    asca
    0.08
    æĻ´
    0.08
    akin
    0.08
    è¿ĺæĺ¯è¦ģ
    0.08
     пÑĢоÑĩ
    0.08
    éľİ
    0.08
    èıĬèĬ±
    0.08
    Activations Density 0.002%

    No Known Activations