© 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. 22577
    Prev
    Next
    INDEX
    Explanations

    "I'm" or "am"

    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
    ician
    -0.27
    æ·»
    -0.26
    åĨ°
    -0.26
    auc
    -0.26
     bindActionCreators
    -0.26
     Posting
    -0.26
    amentals
    -0.26
     coll
    -0.25
     appar
    -0.24
    Beginning
    -0.24
    POSITIVE LOGITS
    ä¸ĢèĦļ
    0.27
    æ´Ĺæīĭ
    0.27
    åģļå®Į
    0.26
    umbs
    0.26
    åħ¨çľģ
    0.25
    æį§
    0.24
    æīĭ
    0.24
    foot
    0.24
    ÑĪение
    0.23
    ryn
    0.23
    Activations Density 0.218%

    No Known Activations