© 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. 130243
    Prev
    Next
    INDEX
    Explanations

    Mentions companies and organizations

    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
    j
    -0.27
    ero
    -0.26
     bun
    -0.25
    ane
    -0.25
    Rep
    -0.25
    ¢
    -0.25
     pron
    -0.25
     пÑĢедмеÑĤ
    -0.24
    Representation
    -0.24
    Entr
    -0.24
    POSITIVE LOGITS
    odb
    0.29
     setters
    0.26
    ·»
    0.26
    å¤ļäºĨ
    0.26
    sville
    0.26
    folios
    0.25
    zsche
    0.25
    ramework
    0.25
    å¤ļå°ij
    0.24
    æľīå¤ļ
    0.24
    Activations Density 0.030%

    No Known Activations