© 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. 33-TRANSCODER-HP
    7. 53350
    Prev
    Next
    INDEX
    Explanations

    coding scripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shell
    -0.31
     Shell
    -0.30
    壳
    -0.28
    -shell
    -0.28
    å¯Ł
    -0.27
     shells
    -0.25
    è¿ŀéĶģ
    -0.25
     capt
    -0.25
     cr
    -0.24
    Cat
    -0.24
    POSITIVE LOGITS
    bx
    0.27
    .scheme
    0.27
    ala
    0.27
    çĸı
    0.26
    好çļĦ
    0.26
    æ¢ĥ
    0.24
    atics
    0.24
    good
    0.24
     Bowie
    0.23
    (expect
    0.23
    Activations Density 0.031%

    No Known Activations