© 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. 12-TRANSCODER-HP
    7. 23770
    Prev
    Next
    INDEX
    Explanations

    prayers and requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phase
    -0.26
     sal
    -0.25
     lining
    -0.25
    åĹĶ
    -0.25
    bert
    -0.25
     Ot
    -0.24
    TypeID
    -0.24
    facet
    -0.24
    OR
    -0.24
    åĪ©
    -0.24
    POSITIVE LOGITS
    èĢģ乡
    0.28
    壶
    0.26
     quanto
    0.25
    æŁĶ软
    0.25
    _NS
    0.24
    表çİ°åĩº
    0.23
     Geschäfts
    0.23
    .LE
    0.23
    hunt
    0.23
    paths
    0.23
    Activations Density 0.001%

    No Known Activations