© 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. 87424
    Prev
    Next
    INDEX
    Explanations

    and

    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
     acquisitions
    -0.30
    %X
    -0.28
    åı«æĪij
    -0.28
    seys
    -0.27
    amax
    -0.27
    .predicate
    -0.25
    ufen
    -0.25
    fox
    -0.25
    ç§ģãģĮ
    -0.25
    åĮĢ
    -0.23
    POSITIVE LOGITS
    家å±ŀ
    0.27
    çĶ³è¯·äºº
    0.27
    rs
    0.27
    æĺ¯ä¸Ģ项
    0.26
    idden
    0.26
    å°¾
    0.25
    éĶļ
    0.25
    产åĩº
    0.24
    åŃIJåŃĻ
    0.24
     Holmes
    0.24
    Activations Density 0.011%

    No Known Activations