© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19786
    Prev
    Next
    INDEX
    Explanations

    machine learning code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    .LocalDate
    -0.06
    æīĢåIJ«
    -0.06
    RAND
    -0.06
     crow
    -0.06
     éc
    -0.06
    ijt
    -0.06
    åĪ°çĽ®åīį
    -0.06
    ä¸ĢèĪ¬éĥ½ä¼ļ
    -0.06
    平平å®ī
    -0.06
    çĶŁçIJĨåѦ
    -0.06
    POSITIVE LOGITS
    heim
    0.07
    opal
    0.05
    foobar
    0.05
    ffen
    0.05
    çİĩ
    0.05
    гл
    0.05
    缴
    0.05
    æŁĶ
    0.05
    ursa
    0.05
    Digit
    0.05
    Activations Density 0.038%

    No Known Activations