© 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. 55943
    Prev
    Next
    INDEX
    Explanations

    masking and masked content

    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
    媳
    -0.12
    ниÑĩ
    -0.10
    icode
    -0.10
    .Transactional
    -0.09
    anness
    -0.09
    åij½
    -0.09
    åħħæ²Ľ
    -0.09
    shaw
    -0.09
    itat
    -0.09
    antry
    -0.09
    POSITIVE LOGITS
    edTextBox
    0.14
    ä¸įä½ı
    0.11
    buster
    0.10
    edList
    0.10
    åŃIJéĩĮ
    0.10
    less
    0.10
    åıŁ
    0.10
    å¾Ĺä½ı
    0.10
    èĶ½
    0.09
    edReader
    0.09
    Activations Density 0.019%

    No Known Activations