© 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. 56797
    Prev
    Next
    INDEX
    Explanations

    land

    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
    ATA
    -0.28
    infeld
    -0.25
    uum
    -0.25
    imating
    -0.25
    plural
    -0.25
    ä¾¿å®ľ
    -0.25
    imates
    -0.24
    å¾Ĺèµ·
    -0.24
     Oregon
    -0.24
    minent
    -0.24
    POSITIVE LOGITS
    èIJ½
    0.27
     Society
    0.26
    åĴ¬
    0.25
     Maiden
    0.25
    _fraction
    0.24
     bite
    0.24
    齿
    0.24
    åįıä¼ļä¼ļéķ¿
    0.24
    åħ¨åŁŁ
    0.23
     Resist
    0.23
    Activations Density 0.003%

    No Known Activations