© 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. 20436
    Prev
    Next
    INDEX
    Explanations

    Prefixes/suffixes followed by specific words

    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
    å¾Ģ
    -0.07
     va
    -0.06
    幸
    -0.05
     group
    -0.05
    ä¸īåĪĨ
    -0.05
    1
    -0.05
    wd
    -0.05
    -
    -0.05
    ìĤ¬
    -0.05
    asl
    -0.05
    POSITIVE LOGITS
    å¾Īå¤ļçݩ家
    0.06
    .Linear
    0.06
    çĶŁæ°£
    0.06
    è·¯å°ıåѦ
    0.06
     keyst
    0.06
    èĭ¦è¾£
    0.06
     Linear
    0.06
    线æĢ§
    0.06
    _birth
    0.06
     consciente
    0.06
    Activations Density 0.042%

    No Known Activations