© 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. 62080
    Prev
    Next
    INDEX
    Explanations

    identity transformations and crisis

    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
    çĸij
    -0.10
    ä¸įå±ij
    -0.09
    ç¥ŀä»Ļ
    -0.09
    ä¸įæĩĤ
    -0.09
    è°£
    -0.08
     Branch
    -0.08
    å·¨
    -0.08
    ä¸Ĭåı¸
    -0.08
    ä¸ĢåıĮ
    -0.08
    éĻįèIJ½
    -0.08
    POSITIVE LOGITS
    身份
    0.27
     identity
    0.26
    çļĦ身份
    0.25
    identity
    0.24
    .identity
    0.23
     Identity
    0.23
    (identity
    0.22
    Identity
    0.22
    _identity
    0.21
     identities
    0.21
    Activations Density 0.229%

    No Known Activations