© 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. 129343
    Prev
    Next
    INDEX
    Explanations

    advice, help

    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
    sticks
    -0.32
     term
    -0.29
    è¶Ł
    -0.26
    itudes
    -0.26
     terme
    -0.26
    亿åħĥ
    -0.26
    åľī
    -0.26
    term
    -0.26
    ÑģÑĤвоваÑĤÑĮ
    -0.25
    INGTON
    -0.24
    POSITIVE LOGITS
     leaked
    0.26
    çīĽ
    0.26
    åIJ¹
    0.25
    æ³Ľ
    0.25
    Bucket
    0.24
    snap
    0.24
    Cow
    0.24
    .qual
    0.24
    çī©ä»·
    0.24
    VC
    0.24
    Activations Density 0.029%

    No Known Activations