© 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. 87960
    Prev
    Next
    INDEX
    Explanations

    Code, SQL, digital issues

    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
    -component
    -0.27
    istics
    -0.25
    ruptcy
    -0.25
     Fer
    -0.24
    inded
    -0.24
    FTER
    -0.24
     component
    -0.24
    urate
    -0.24
    line
    -0.24
    ýt
    -0.24
    POSITIVE LOGITS
    thal
    0.27
    èµ°
    0.26
    顶
    0.26
    cy
    0.25
    çIJĨ
    0.25
    iche
    0.24
    æĸĻ
    0.24
    åİĺ
    0.24
     htt
    0.24
    иÑĩ
    0.24
    Activations Density 0.003%

    No Known Activations