© 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. 129538
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ä¸įçĦ¶
    -0.26
    Commission
    -0.26
     pronto
    -0.26
    绣çŃ¹æİ¨è¿Ľ
    -0.26
    è¿Ļ段
    -0.25
     ax
    -0.25
    ament
    -0.24
    éħ¬
    -0.24
    onto
    -0.23
    åĨįåİ»
    -0.23
    POSITIVE LOGITS
    ä¹ĭå¤ľ
    0.27
    ivities
    0.27
    дел
    0.25
    .BL
    0.25
    éĺŁä¼į建设
    0.24
    sass
    0.24
    ativ
    0.24
    аÑĢа
    0.23
    fk
    0.23
    anka
    0.23
    Activations Density 0.009%

    No Known Activations