© 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. 22-TRANSCODER-HP
    7. 98133
    Prev
    Next
    INDEX
    Explanations

    Random topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _=
    -0.26
    mond
    -0.25
    -marker
    -0.24
    âĤĢ
    -0.24
     getopt
    -0.24
    -related
    -0.24
    remen
    -0.24
    _='
    -0.23
    KHR
    -0.23
    ì°°
    -0.23
    POSITIVE LOGITS
    _exact
    0.26
    Edition
    0.26
    mp
    0.25
    趣åij³
    0.25
    ãĤ¹ãĤ¿ãĥ³
    0.25
    antage
    0.24
    íĮ¬
    0.24
     discussion
    0.24
    eff
    0.24
    贯穿
    0.24
    Activations Density 0.088%

    No Known Activations