© 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. 22088
    Prev
    Next
    INDEX
    Explanations

    json object keys and values

    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
    VAS
    -0.09
    tro
    -0.09
    çĮĸ
    -0.09
    éªĬ
    -0.09
    å°±ç®Ĺæĺ¯
    -0.09
    ä¹İ
    -0.09
    åħ¨æµģç¨ĭ
    -0.09
    两èĢħ
    -0.09
    åĴĮåľ°åĮº
    -0.08
    çħ³
    -0.08
    POSITIVE LOGITS
    zew
    0.09
    meer
    0.08
    _foot
    0.08
    artin
    0.08
    yster
    0.07
    encers
    0.07
    mpp
    0.07
     Ngh
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    èľ·
    0.07
    Activations Density 0.696%

    No Known Activations