© 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. 20513
    Prev
    Next
    INDEX
    Explanations

    difficulty and hardness

    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
    anim
    -0.07
    umÄģ
    -0.06
    ']}</
    -0.06
    неÑĤ
    -0.06
    é¢ĦæľŁçļĦ
    -0.06
    çļĦé¢ĦæľŁ
    -0.06
     erwartet
    -0.06
    ç¼ĺæķħ
    -0.06
    rame
    -0.06
    éłIJæľŁ
    -0.06
    POSITIVE LOGITS
    èĢģ
    0.06
    åĨį
    0.05
    èĽĽ
    0.05
    姿
    0.05
    åħµ
    0.05
    å°±ä¸į
    0.05
    ç³»ç»ŁæĢ§
    0.05
    计价
    0.05
    utz
    0.05
    mont
    0.05
    Activations Density 0.017%

    No Known Activations