© 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. 17493
    Prev
    Next
    INDEX
    Explanations

    but followed by contrastive offers or explanations

    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
    omen
    -0.06
    è°ĭ
    -0.05
    ç³»
    -0.05
    çĽ²
    -0.05
    .setdefault
    -0.05
    ignor
    -0.05
    en
    -0.05
    iced
    -0.05
    åħ¹
    -0.05
    ืà¸Ļ
    -0.05
    POSITIVE LOGITS
    GRA
    0.06
    dna
    0.06
    åį«ä¸ľ
    0.06
    ptos
    0.06
    rozum
    0.06
    ãģĵãģªãģĦ
    0.06
    ibri
    0.06
    abri
    0.05
    erus
    0.05
    ä¸ĩ亿ç¾İåħĥ
    0.05
    Activations Density 0.008%

    No Known Activations