© 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. 27-TRANSCODER-HP
    7. 8674
    Prev
    Next
    INDEX
    Explanations

    web content snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Affero
    -0.25
    åŁ
    -0.25
    -fed
    -0.24
    ä¹Łåıªæľī
    -0.24
    è¿ĺå¾Ĺ
    -0.24
    judge
    -0.24
    _PE
    -0.24
    etheless
    -0.24
    forge
    -0.23
    FIT
    -0.23
    POSITIVE LOGITS
    OLS
    0.28
    åįĪåIJİ
    0.27
    ellar
    0.27
     tarde
    0.26
    olds
    0.26
    elder
    0.25
     unique
    0.25
    ceptor
    0.25
    amba
    0.24
    级
    0.24
    Activations Density 0.002%

    No Known Activations