© 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. 25-TRANSCODER-HP
    7. 107647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trys
    -0.29
     CDDL
    -0.28
    bery
    -0.28
    èĥĮçĿĢ
    -0.27
    ousel
    -0.27
    ished
    -0.26
    ACCEPT
    -0.26
    inox
    -0.26
    atorial
    -0.26
    åĨĴçĿĢ
    -0.25
    POSITIVE LOGITS
    å½¢æĢģ
    0.30
    åĻ¨æ¢°
    0.29
    å®ļ
    0.28
    主ä¹ī
    0.27
     ÑģиÑĤÑĥ
    0.27
     Äijá»ĭnh
    0.26
     tô
    0.26
     migrate
    0.26
    äºĮ
    0.26
    æĥħèĬĤ
    0.26
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.