© 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. 27-TRANSCODER-HP
    7. 8650
    Prev
    Next
    INDEX
    Explanations

    xA

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     digestive
    -0.36
     digestion
    -0.33
    循çݯ
    -0.33
     sanitation
    -0.31
    æ¶ĪåĮĸ
    -0.31
     circulation
    -0.29
    ä½ľæģ¯
    -0.28
     nutrition
    -0.28
     revolution
    -0.28
    è½®åĽŀ
    -0.27
    POSITIVE LOGITS
     degree
    0.25
    åı°ä¸Ĭ
    0.25
    æĥħèĬĤ
    0.25
     Kushner
    0.24
    Transfer
    0.24
    ÏĪ
    0.23
     overd
    0.23
     Ä°z
    0.23
     cú
    0.23
    _COMPAT
    0.23
    Activations Density 0.005%

    No Known Activations