© 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. 24667
    Prev
    Next
    INDEX
    Explanations

    Sentence structure/grammar

    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
     Pays
    -0.26
    女人
    -0.26
     struggled
    -0.26
    ä¾Ŀ
    -0.26
    istically
    -0.26
    ä¸įä¹ħåīį
    -0.26
     mist
    -0.25
    пи
    -0.25
    .subject
    -0.25
    ograf
    -0.25
    POSITIVE LOGITS
    null
    0.30
    å½¢æĪIJçļĦ
    0.28
    ıklı
    0.28
    .null
    0.27
    æĽ´
    0.27
     Null
    0.27
    æĹłéĻIJ
    0.25
    veyor
    0.25
     null
    0.25
    enary
    0.24
    Activations Density 0.002%

    No Known Activations