© 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. 20225
    Prev
    Next
    INDEX
    Explanations

    farther or further direction

    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
    波波
    -0.06
    ikko
    -0.06
    ÃŃs
    -0.06
    itif
    -0.06
     finer
    -0.06
    zilla
    -0.06
    -hover
    -0.06
     sometime
    -0.06
    å½»
    -0.05
    ä¼ļæĻ¤
    -0.05
    POSITIVE LOGITS
    åı¯çĶ³è¯·
    0.06
    ads
    0.06
    anded
    0.05
    inas
    0.05
    tons
    0.05
    trl
    0.05
    ad
    0.05
    ä¸įéľĢ
    0.05
    ä¸įè´Łè´£
    0.05
    大éĥ¨
    0.05
    Activations Density 0.005%

    No Known Activations