© 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. 12-TRANSCODER-HP
    7. 22595
    Prev
    Next
    INDEX
    Explanations

    mentioned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıŁ
    -0.32
    mares
    -0.27
    opian
    -0.27
     GREAT
    -0.26
    carbon
    -0.26
    ãĥĹãĥ©ãĤ¹
    -0.25
    æķ´ä½ĵ
    -0.24
    æľ½
    -0.24
    -white
    -0.24
    iets
    -0.24
    POSITIVE LOGITS
    _slave
    0.24
    sla
    0.24
    ÓĢ
    0.24
    å½±éŁ³
    0.24
    ää
    0.23
     uns
    0.23
    亲身
    0.23
    ÃĹ</
    0.23
     Hands
    0.23
    .preventDefault
    0.23
    Activations Density 0.002%

    No Known Activations