© 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. 18205
    Prev
    Next
    INDEX
    Explanations

    '/f' prefixes or "$f"

    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
    vene
    -0.06
    åĪ«è¯´
    -0.06
    리íĬ¸
    -0.06
    веÑĢе
    -0.05
    è¹Ń
    -0.05
    hend
    -0.05
    ạy
    -0.05
    ç¥ŀ级
    -0.05
     gelingt
    -0.05
    çªģçł´æĢ§
    -0.05
    POSITIVE LOGITS
    $f
    0.06
     /
    0.06
    ossa
    0.06
    以åıĬ
    0.05
     thai
    0.05
    $r
    0.05
    $s
    0.05
     wr
    0.05
    azzo
    0.05
    /f
    0.05
    Activations Density 0.002%

    No Known Activations