© 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. 19826
    Prev
    Next
    INDEX
    Explanations

    bullets

    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
    åĨ³çŃĸ
    -0.06
    boro
    -0.05
     shadow
    -0.05
    uristic
    -0.05
    fert
    -0.05
    åĴĮéĹ®é¢ĺ
    -0.05
    审
    -0.05
    æ«
    -0.05
    orem
    -0.05
    å·¡
    -0.05
    POSITIVE LOGITS
    åħļç»Ħ书记
    0.07
     evid
    0.06
    undi
    0.06
     unif
    0.06
     Pron
    0.06
    ä¸ĢçĽĨ
    0.06
    _-_
    0.05
     Ukraina
    0.05
    æľºåħ³
    0.05
    ieben
    0.05
    Activations Density 0.007%

    No Known Activations