© 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. 111394
    Prev
    Next
    INDEX
    Explanations

    Finding or determining the best

    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
    æĤ»
    -0.26
     ourselves
    -0.24
    idl
    -0.24
    lug
    -0.24
    recover
    -0.24
    quate
    -0.23
    vé
    -0.23
    defs
    -0.23
    (proto
    -0.23
    à¹Ģà¸Ńà¸ģ
    -0.23
    POSITIVE LOGITS
    åıĮè¾¹
    0.28
    ä¸ĭéĻį
    0.28
    ernet
    0.27
    使
    0.27
    åIJijä¸ĭ
    0.26
     lle
    0.26
    æįŁèĢĹ
    0.25
    /generated
    0.25
    yr
    0.25
    éĻįä½İ
    0.25
    Activations Density 0.006%

    No Known Activations