© 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. 19210
    Prev
    Next
    INDEX
    Explanations

    legal citations or parentheticals

    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
    èĥ¤
    -0.06
    обÑīе
    -0.05
    ishly
    -0.05
    ajah
    -0.05
    o
    -0.05
    å·²æľī
    -0.05
     NS
    -0.05
    ãģªãģĦ
    -0.05
    ickle
    -0.05
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.05
    POSITIVE LOGITS
     lluv
    0.07
    abyrin
    0.07
    raž
    0.06
    åĶ¯ä¸Ģä¸Ģ家
    0.06
    ammo
    0.06
    uned
    0.06
     Wasch
    0.06
    indr
    0.06
    langs
    0.06
    sste
    0.06
    Activations Density 0.005%

    No Known Activations