© 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. 24950
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
    è±ļ
    -0.27
    çī¹å®ļ
    -0.26
    onis
    -0.25
    缸åħ³äººåijĺ
    -0.25
    oe
    -0.25
    ṡ
    -0.25
    ourg
    -0.25
    æĮĩåIJij
    -0.24
     kep
    -0.24
     Ach
    -0.24
    POSITIVE LOGITS
    ä¼ļ产çĶŁ
    0.26
    ¡°
    0.26
    ismic
    0.26
    omba
    0.26
    arend
    0.25
    swer
    0.24
    iedo
    0.24
    -backend
    0.24
    egl
    0.24
    etypes
    0.24
    Activations Density 0.003%

    No Known Activations