© 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. 18825
    Prev
    Next
    INDEX
    Explanations

    pay tax

    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
    ROID
    -0.07
     inciden
    -0.06
    acons
    -0.06
     diá»ħn
    -0.06
    anship
    -0.06
    aland
    -0.06
    erto
    -0.06
    resti
    -0.06
     kurs
    -0.06
    èĩªå·±æĥ³
    -0.06
    POSITIVE LOGITS
    åįľ
    0.06
    ÙĬØ´
    0.05
     pref
    0.05
     ÙĤÙĦÙĬ
    0.05
    rier
    0.05
    comp
    0.05
    foot
    0.05
    端æŃ£
    0.04
     suffice
    0.04
    CH
    0.04
    Activations Density 0.036%

    No Known Activations