© 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. 23-TRANSCODER-HP
    7. 24671
    Prev
    Next
    INDEX
    Explanations

    Locations and buildings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     welt
    -0.25
     italian
    -0.25
     Weg
    -0.25
     favour
    -0.25
     æµ
    -0.24
    @yahoo
    -0.24
    opot
    -0.24
    sem
    -0.24
    iais
    -0.24
     Indust
    -0.24
    POSITIVE LOGITS
    ibrator
    0.28
    ervative
    0.28
    æĸ°åŁİ
    0.26
    days
    0.26
    named
    0.25
    è¦ģç´§
    0.24
    oystick
    0.24
    çļĦ羣å®ŀ
    0.24
    å°ıéķĩ
    0.24
     Sachs
    0.24
    Activations Density 0.004%

    No Known Activations