© 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. 36109
    Prev
    Next
    INDEX
    Explanations

    who followed by a verb

    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
    lı
    -0.11
    lah
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    ally
    -0.10
    ãģĹãģ¾
    -0.10
    {}",
    -0.09
    ono
    -0.09
    ä¸ĢèĪ¬äºº
    -0.09
    éĴµ
    -0.09
    ãģĤãĤĬãģ¾ãģĻ
    -0.09
    POSITIVE LOGITS
    soever
    0.16
    oping
    0.14
    ãģ¹ãģį
    0.13
    've
    0.12
    /how
    0.11
    ’ve
    0.09
    åıĪèĥ½
    0.09
    ï¸
    0.09
    'd
    0.09
    abi
    0.09
    Activations Density 0.112%

    No Known Activations