© 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. 14-TRANSCODER-HP
    7. 41028
    Prev
    Next
    INDEX
    Explanations

    Dashes and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rib
    -0.28
    arden
    -0.28
    колÑĮ
    -0.25
    ARP
    -0.25
    Ñĩе
    -0.25
    haft
    -0.25
    ibal
    -0.24
    è°IJ
    -0.24
    epar
    -0.24
     Predator
    -0.24
    POSITIVE LOGITS
    /or
    0.30
    /OR
    0.26
    åĥļ
    0.26
     coast
    0.25
    æĸĩåĮĸçļĦ
    0.25
    .ascii
    0.25
    åľ»
    0.23
    Issue
    0.23
    æĥ³ä¸įåĪ°
    0.23
     zug
    0.23
    Activations Density 2.106%

    No Known Activations