© 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. 17751
    Prev
    Next
    INDEX
    Explanations

    aid, assist, assistance

    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
    lit
    -0.06
    æĹĭ
    -0.06
     esp
    -0.06
    请æĶ¾å¿ĥ
    -0.06
    æĬķèµĦåŁºéĩij
    -0.05
    skosten
    -0.05
     recipro
    -0.05
    æºĢ
    -0.05
     lit
    -0.05
     paz
    -0.05
    POSITIVE LOGITS
    åŀĭ
    0.06
     bele
    0.06
     Proper
    0.05
    uth
    0.05
    ovil
    0.05
    fdc
    0.05
     пÑĢибли
    0.05
    ä¸ĭè¾¾
    0.05
    ziÄĻki
    0.05
    bog
    0.05
    Activations Density 0.023%

    No Known Activations