© 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. 24103
    Prev
    Next
    INDEX
    Explanations

    programming code/text

    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
    XObject
    -0.26
    annah
    -0.26
    film
    -0.25
    åİļ
    -0.25
    è¿Ļé¦ĸ
    -0.25
    ?("
    -0.25
    /repos
    -0.24
    åĩĢåĢ¼
    -0.24
     referred
    -0.24
    æµĵ度
    -0.24
    POSITIVE LOGITS
     figures
    0.28
    жд
    0.27
    eba
    0.26
    este
    0.26
     emerg
    0.26
    çļĦçIJĨçĶ±
    0.26
    fty
    0.25
     dy
    0.25
    Turn
    0.24
     Blind
    0.24
    Activations Density 0.002%

    No Known Activations