© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
    sstr
    -0.08
    ÑģÑĤвием
    -0.07
    schaften
    -0.07
    fru
    -0.06
    anner
    -0.06
    åı£ä¸ŃçļĦ
    -0.06
    sver
    -0.06
    /Instruction
    -0.06
    gran
    -0.06
    abbr
    -0.06
    POSITIVE LOGITS
    izable
    0.06
    ifiable
    0.06
    çļĦè¿ĺæĺ¯
    0.06
    able
    0.06
    eras
    0.05
    ably
    0.05
    одо
    0.05
    æĢ§åľ°
    0.05
    ization
    0.05
    اÙĭ
    0.05
    Activations Density 0.010%

    No Known Activations