© 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. 24-TRANSCODER-HP
    7. 149767
    Prev
    Next
    INDEX
    Explanations

    unstructured data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大è¡Ĺ
    -0.28
    å±ķå¼Ģ
    -0.26
    tility
    -0.25
    æŃ£å½ĵ
    -0.25
    tabl
    -0.24
    å¿Ĩ
    -0.24
    mand
    -0.24
    带æĿ¥æĽ´å¤ļ
    -0.23
    rega
    -0.23
    åı¦ä¸Ģä½į
    -0.23
    POSITIVE LOGITS
    apper
    0.26
    acking
    0.25
    kehr
    0.25
    Ty
    0.25
     achievement
    0.25
    anken
    0.24
     moi
    0.24
    presso
    0.24
    acco
    0.24
     Ven
    0.24
    Activations Density 0.030%

    No Known Activations