© 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. 112562
    Prev
    Next
    INDEX
    Explanations

    1

    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
    POSIT
    -0.32
    ivan
    -0.27
    ASET
    -0.26
    æĦıä¹īä¸Ĭ
    -0.26
    uttle
    -0.26
    Filtered
    -0.25
    eut
    -0.25
     posit
    -0.25
     кÑĥлÑĮÑĤ
    -0.24
    åĢĻ
    -0.24
    POSITIVE LOGITS
    processing
    0.30
    ç§ĺ书
    0.26
    extField
    0.26
     ca
    0.26
     processing
    0.26
    vere
    0.25
    escaping
    0.25
    bor
    0.25
    ä¸ĵ
    0.24
    um
    0.24
    Activations Density 0.000%

    No Known Activations