© 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. 22348
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    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
    reek
    -0.28
    ä¿ĿåŃĺ
    -0.26
     posing
    -0.26
    Blake
    -0.25
    phia
    -0.25
    ropolis
    -0.25
    çŃīåĢĻ
    -0.25
    çģ«å±±
    -0.25
     beaches
    -0.25
     awaited
    -0.25
    POSITIVE LOGITS
    槽
    0.27
    åº
    0.27
    onet
    0.27
    è¦ĨçĽĸçİĩ
    0.26
    itore
    0.26
    lot
    0.26
    :message
    0.26
    onn
    0.25
    æ´Ļ
    0.25
    breaker
    0.25
    Activations Density 0.007%

    No Known Activations