© 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. 19025
    Prev
    Next
    INDEX
    Explanations

    same result or correct answer

    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
    utant
    -0.06
    éĢ»
    -0.06
    ä¸İåħ±
    -0.06
    itante
    -0.06
    bjerg
    -0.06
     völ
    -0.06
    isphere
    -0.06
    обÑĢазова
    -0.06
    缼
    -0.06
    ç¡Ģ
    -0.06
    POSITIVE LOGITS
    æĪIJ人
    0.06
    pose
    0.05
    ETT
    0.05
    bo
    0.05
    äººä¸ºæľ¬
    0.05
    rome
    0.05
    íĺĦ
    0.05
    ä¸į失
    0.05
    zi
    0.05
    壮è§Ĥ
    0.05
    Activations Density 0.007%

    No Known Activations