© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9356
    Prev
    Next
    INDEX
    Explanations

    any

    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
    åıĤ
    -0.09
    è£ģ
    -0.08
    دÙĪ
    -0.08
    bet
    -0.08
    æı½
    -0.08
     nor
    -0.08
    .console
    -0.07
    åIJĦé¡¹å·¥ä½ľ
    -0.07
    anzi
    -0.07
     proverb
    -0.07
    POSITIVE LOGITS
    åĮĸ身
    0.10
    çĢijå¸ĥ
    0.10
    vsp
    0.10
    ÑĤÑĮ
    0.09
    è¿Ļæł·è¯´
    0.09
    Ë¡
    0.09
    cala
    0.09
    lore
    0.09
    .ReadOnly
    0.09
    thing
    0.09
    Activations Density 0.063%

    No Known Activations