© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88201
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ismet
    -0.28
    thin
    -0.28
    isz
    -0.25
    éªĪ
    -0.25
    ä¹Łèĥ½
    -0.24
     always
    -0.24
    amon
    -0.24
    .Env
    -0.23
    mel
    -0.23
     MON
    -0.23
    POSITIVE LOGITS
    ä½łçİ°åľ¨
    0.25
    åľ°ä¸Ń
    0.25
    ergy
    0.25
    emphasis
    0.25
    æ¿Ĵ临
    0.24
    çĤ¹éĴŁ
    0.24
    毯
    0.24
    others
    0.24
    éĿ¢ä¸´çĿĢ
    0.23
    çİĩ为
    0.23
    Activations Density 0.005%

    No Known Activations