© 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. 7249
    Prev
    Next
    INDEX
    Explanations

    naphthalene

    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
    è²Į
    -0.09
    Vars
    -0.09
    ities
    -0.08
    agen
    -0.08
    erne
    -0.08
    çĮ·
    -0.08
    ваÑĢ
    -0.08
    ĭ
    -0.08
    ìĭŃ
    -0.08
    ãĥªãĥ³ãĤ°
    -0.08
    POSITIVE LOGITS
    çħ
    0.12
    lace
    0.09
    ertext
    0.09
    iable
    0.09
     sobie
    0.09
    éĩįä¸Ńä¹ĭéĩį
    0.09
    åĿ¨
    0.09
    æ±Łåİ¿
    0.09
    ting
    0.09
    matic
    0.09
    Activations Density 0.015%

    No Known Activations