© 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. 22740
    Prev
    Next
    INDEX
    Explanations

    Operating systems and versions

    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
    łģ
    -0.27
    ä¸Ģçĵ¶
    -0.26
    绳
    -0.25
    eren
    -0.24
    ator
    -0.24
    Finder
    -0.24
    enor
    -0.24
    abil
    -0.24
    èĢĮåİ»
    -0.24
    ifer
    -0.24
    POSITIVE LOGITS
    witter
    0.27
     smack
    0.27
    yre
    0.27
    ippo
    0.26
    -position
    0.25
    tempt
    0.25
    (wp
    0.25
    	wp
    0.24
    YP
    0.24
    houette
    0.24
    Activations Density 0.019%

    No Known Activations