© 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. 10940
    Prev
    Next
    INDEX
    Explanations

    extinguish, fire, out

    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
    æijĦ
    -0.09
    onis
    -0.09
    åĬ³åĬ¨èĢħ
    -0.09
    ç²¾ç¥ŀ
    -0.09
    ascript
    -0.09
    roy
    -0.09
    èµ°åľ¨
    -0.09
    åĢ¾åIJ¬
    -0.09
    æ®Ĭ
    -0.09
    acket
    -0.08
    POSITIVE LOGITS
    çĨĦ
    0.24
     extingu
    0.15
    çģ«èĬ±
    0.13
    çĩĥ
    0.13
    çģŃ
    0.12
    çĩĥæĸĻ
    0.12
    åıijæĶ¹
    0.12
    çģŃçģ«
    0.12
    çģ«çĦ°
    0.12
    çģ¯çģ«
    0.11
    Activations Density 0.050%

    No Known Activations