© 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. 97713
    Prev
    Next
    INDEX
    Explanations

    code/testing

    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
    åĪĹ
    -0.27
    -f
    -0.26
    ã
    -0.25
    çĥŃçĤ¹
    -0.24
     esc
    -0.24
     buzz
    -0.24
    Orth
    -0.24
     vẽ
    -0.24
    uding
    -0.24
    ä¸Ģç±»
    -0.24
    POSITIVE LOGITS
    /tiny
    0.26
    åİļåİļçļĦ
    0.26
    reat
    0.26
    ously
    0.25
    REAT
    0.25
    fleet
    0.25
    è§ĦåĪĴ建设
    0.25
     Sam
    0.24
    åħ¨åijĺ
    0.24
     almonds
    0.24
    Activations Density 0.001%

    No Known Activations