© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21077
    Prev
    Next
    INDEX
    Explanations

    dk, SC, lash, helmet, frame, output, use

    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
     поклон
    -0.06
     Spur
    -0.05
    åı©
    -0.05
     specially
    -0.05
    -Jul
    -0.05
    Nya
    -0.05
    etter
    -0.05
    -den
    -0.05
    ere
    -0.05
    har
    -0.05
    POSITIVE LOGITS
    SCP
    0.06
    SC
    0.06
    å¹³è¡Į
    0.05
    éĢĴ
    0.05
     Marr
    0.05
    éĢ»è¾ij
    0.05
    é¦
    0.05
    orde
    0.05
    è¿ĩæĿ¥äºĨ
    0.05
    ä»»åħį
    0.05
    Activations Density 0.133%

    No Known Activations