© 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. 18420
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    s
    -0.10
    im
    -0.06
    tract
    -0.06
    а
    -0.06
    semble
    -0.05
    ÙĦاÙĭ
    -0.05
    Ñĭ
    -0.05
    R
    -0.05
    ات
    -0.05
    ward
    -0.05
    POSITIVE LOGITS
    /disable
    0.08
    ydi
    0.07
    umé
    0.07
    ìĦľ
    0.07
    evo
    0.07
    ecker
    0.07
    puis
    0.07
    Ø©
    0.06
    Ùĩ
    0.06
    yen
    0.06
    Activations Density 0.009%

    No Known Activations