© 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. 19250
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     Specific
    -0.06
     schem
    -0.06
     specific
    -0.06
    ê±°
    -0.06
    ãĤĬãģ¨
    -0.06
    itled
    -0.06
    ttp
    -0.06
    max
    -0.05
     max
    -0.05
    çĽĽå¤§
    -0.05
    POSITIVE LOGITS
    è´«
    0.05
    QC
    0.05
    âu
    0.05
    pizza
    0.05
    使人
    0.05
    èĪ¬
    0.05
    èĪ¬çļĦ
    0.05
    ozn
    0.05
    AC
    0.05
    æĹłæŀģ
    0.05
    Activations Density 0.015%

    No Known Activations