© 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. 20182
    Prev
    Next
    INDEX
    Explanations

    recounting stories, narration, telling tales

    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
    ائÙĤ
    -0.09
    rez
    -0.07
    asz
    -0.06
    hong
    -0.06
    hack
    -0.06
    jana
    -0.06
    ä¸İ伦
    -0.06
    icken
    -0.06
    deaux
    -0.06
    anze
    -0.06
    POSITIVE LOGITS
    embali
    0.06
    gir
    0.06
    eterangan
    0.05
     disturbed
    0.05
    our
    0.05
    çĻ½éľ²
    0.05
    åĪ°é«ĺ
    0.05
    -sided
    0.05
    åŀĭ
    0.05
    avel
    0.05
    Activations Density 0.002%

    No Known Activations