© 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. 37561
    Prev
    Next
    INDEX
    Explanations

    to 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
    姻
    -0.11
    à¸Ħà¸ĩ
    -0.10
    nown
    -0.09
    åħĦå¼Ł
    -0.09
    UDA
    -0.09
    éģĩåĪ°äºĨ
    -0.08
    udit
    -0.08
    uda
    -0.08
    _ONCE
    -0.08
    peg
    -0.08
    POSITIVE LOGITS
    elts
    0.09
    reno
    0.09
     raspberry
    0.09
    æ³Ľ
    0.09
    elic
    0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
     indef
    0.08
    æѤç§į
    0.08
    管å±Ģ
    0.08
    _subtype
    0.08
    Activations Density 0.141%

    No Known Activations