© 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. 22999
    Prev
    Next
    INDEX
    Explanations

    Business contexts

    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
    izarre
    -0.27
     dumping
    -0.26
     Vig
    -0.25
     Programmer
    -0.25
    hamster
    -0.24
     endlessly
    -0.24
    oes
    -0.23
    —one
    -0.23
     dump
    -0.23
    dsn
    -0.23
    POSITIVE LOGITS
    TY
    0.28
     Hess
    0.26
    atur
    0.25
    Ñĥж
    0.25
    æĪ·å¤ĸ
    0.25
    å§Ķåī¯ä¹¦è®°
    0.24
    atics
    0.24
    obe
    0.24
    arine
    0.24
    atform
    0.23
    Activations Density 0.004%

    No Known Activations