© 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. 112062
    Prev
    Next
    INDEX
    Explanations

    and, or

    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
     Fraser
    -0.30
     triple
    -0.29
    fr
    -0.28
    Fr
    -0.26
    .TypeOf
    -0.24
    thesize
    -0.24
    pub
    -0.24
    ä¿¡å¿ĥ
    -0.23
    library
    -0.23
    kind
    -0.23
    POSITIVE LOGITS
    ErrorException
    0.31
    åĬį
    0.25
    amat
    0.24
    åħ»
    0.24
    äºĨ解ä¸Ģä¸ĭ
    0.24
     jot
    0.24
    åīij
    0.24
    imoto
    0.24
    ibbon
    0.24
    ])**
    0.24
    Activations Density 0.020%

    No Known Activations