© 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. 97672
    Prev
    Next
    INDEX
    Explanations

    Temptation

    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
    åħ¸èĮĥ
    -0.26
    Uber
    -0.26
    ensch
    -0.26
    åįķä¸Ģ
    -0.25
    uito
    -0.24
     phép
    -0.24
    è¯ĦåĪ¤
    -0.23
    antis
    -0.23
    åıį对
    -0.23
    æĺĤè´µ
    -0.23
    POSITIVE LOGITS
     desires
    0.25
    .setParameter
    0.25
    ;break
    0.24
     jurisdiction
    0.24
    rowad
    0.23
    orary
    0.23
    åħĥå·¦åı³
    0.23
    morgan
    0.23
    ous
    0.23
     desired
    0.23
    Activations Density 0.028%

    No Known Activations