© 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. 129546
    Prev
    Next
    INDEX
    Explanations

    ist

    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
    emd
    -0.30
    eah
    -0.28
    {*
    -0.27
    åľºåĿĩ
    -0.25
    esub
    -0.25
    ÐļÑĥпиÑĤÑĮ
    -0.25
     subdivisions
    -0.25
    sink
    -0.25
    vendors
    -0.24
    LOCKS
    -0.24
    POSITIVE LOGITS
    èµĭ
    0.29
    Pol
    0.27
     Pol
    0.26
    ãģŁãģ¡
    0.26
    ä¸įèĥ½åĨį
    0.26
    åĢij
    0.25
     rather
    0.25
    rico
    0.25
    åijĺå·¥
    0.25
    Ur
    0.24
    Activations Density 0.013%

    No Known Activations