© 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. 23-TRANSCODER-HP
    7. 24858
    Prev
    Next
    INDEX
    Explanations

    Arabic/foreign language/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èľľ
    -0.27
    åĨĴçĿĢ
    -0.25
     Tout
    -0.24
    owing
    -0.24
    æ¶İ
    -0.23
    æĹłè®º
    -0.23
     Meh
    -0.23
    æĺ¯ä¸Ģ
    -0.23
    åįıä¼ļä¼ļåijĺ
    -0.23
    为æĤ¨
    -0.23
    POSITIVE LOGITS
     INCIDENT
    0.28
    (cos
    0.24
    æĻķ
    0.24
     breached
    0.23
     Cosmos
    0.23
     Firm
    0.23
    .Cos
    0.22
    @hotmail
    0.22
    åĵĪåĵĪ
    0.22
    .sec
    0.22
    Activations Density 0.008%

    No Known Activations