© 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. 57611
    Prev
    Next
    INDEX
    Explanations

    boy/boys

    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
    assen
    -0.24
    è°ĭ
    -0.24
    utherland
    -0.23
    并åIJij
    -0.23
    cape
    -0.23
    butt
    -0.23
    cro
    -0.22
    临
    -0.22
    ories
    -0.22
     unsur
    -0.22
    POSITIVE LOGITS
    ilo
    0.26
    IVEN
    0.25
    ended
    0.25
    LOBAL
    0.24
    æľŁçĽ¼
    0.23
    nton
    0.23
    æ¿®
    0.23
    enders
    0.22
    åħ¼é¡¾
    0.22
    éĢ
    0.22
    Activations Density 0.081%

    No Known Activations