© 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. 31-TRANSCODER-HP
    7. 19067
    Prev
    Next
    INDEX
    Explanations

    Political figures/organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯į
    -0.27
    aac
    -0.26
     Overs
    -0.26
    ner
    -0.25
    yer
    -0.25
    /features
    -0.24
    urance
    -0.24
    åı¯è§Ĥ
    -0.24
    ä¸Ĭ游
    -0.24
    hum
    -0.24
    POSITIVE LOGITS
    ç½ķ
    0.28
    ç²¾
    0.28
    棱
    0.28
    #__
    0.26
    enus
    0.26
    pré
    0.26
     Raises
    0.26
    æł¸
    0.26
    Addon
    0.25
    à¤Ľ
    0.25
    Activations Density 0.137%

    No Known Activations