© 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. 98248
    Prev
    Next
    INDEX
    Explanations

    page or file

    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
    å¦Ĥæľīä¾µæĿĥ
    -0.26
    å¼ĭ
    -0.26
    (pref
    -0.24
     Nz
    -0.24
    ophage
    -0.24
    Sorting
    -0.24
    (rank
    -0.24
    itational
    -0.24
    preh
    -0.23
     mach
    -0.23
    POSITIVE LOGITS
    tal
    0.28
    nej
    0.27
    ç»Ļåĩº
    0.26
    sim
    0.25
     se
    0.25
    onia
    0.25
    ettel
    0.25
     ÃŃ
    0.24
    emen
    0.24
    rieg
    0.24
    Activations Density 0.032%

    No Known Activations