© 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. 19258
    Prev
    Next
    INDEX
    Explanations

    riffs and rhythms

    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
    vs
    -0.06
    ÙIJÙij
    -0.05
    æī¯
    -0.05
     airy
    -0.05
    åĪĨä¼ļ
    -0.05
    离
    -0.05
    CS
    -0.05
    çł
    -0.05
    å¾Ĺèµ·
    -0.05
    jd
    -0.05
    POSITIVE LOGITS
    engel
    0.07
    çİĭéģĵ
    0.07
    ãĤīãģĹãģĦ
    0.07
    typ
    0.06
     warmed
    0.06
    trend
    0.06
    åħ¸åŀĭçļĦ
    0.06
    batas
    0.06
    abet
    0.06
    lement
    0.06
    Activations Density 0.002%

    No Known Activations