© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18137
    Prev
    Next
    INDEX
    Explanations

    body parts and associated actions

    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
    è¿İæĿ¥äºĨ
    -0.05
     exposure
    -0.05
    chema
    -0.05
    ergi
    -0.05
    å¯¹æľ¬æ¬¡
    -0.05
    assic
    -0.05
    avat
    -0.05
     gran
    -0.05
    cam
    -0.05
    arming
    -0.05
    POSITIVE LOGITS
    ears
    0.06
    koÅĽci
    0.06
     liev
    0.05
    esto
    0.05
     effectiveness
    0.05
    leÅŁtir
    0.05
     theirs
    0.05
     effective
    0.05
     обÑĬедин
    0.05
    -through
    0.05
    Activations Density 0.003%

    No Known Activations