© 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. 8928
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    edics
    -0.28
    ä»ħä¾Ľ
    -0.24
    vfs
    -0.24
    iard
    -0.24
    è¢Ĥ
    -0.24
     Private
    -0.23
    转åıĺ为
    -0.23
    enderit
    -0.23
    edic
    -0.23
    lok
    -0.23
    POSITIVE LOGITS
    itto
    0.28
    adamente
    0.26
    å¯Ĵ
    0.26
    翼
    0.25
    .Scope
    0.24
    cheon
    0.24
    éĸĭæĶ¾
    0.24
    _ANDROID
    0.24
    å¼ĺ
    0.24
    éķľå¤´
    0.24
    Activations Density 0.005%

    No Known Activations