© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9357
    Prev
    Next
    INDEX
    Explanations

    quite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.29
    -init
    -0.28
    lane
    -0.26
    ix
    -0.26
    ive
    -0.26
    ab
    -0.26
     ERR
    -0.25
    nge
    -0.24
    éħ·
    -0.24
    hq
    -0.24
    POSITIVE LOGITS
    pty
    0.29
    æľ¦èĥ§
    0.26
    ä¸ĢæŶ
    0.25
    èѬå¦Ĥ
    0.25
    ä¸Ģåı£æ°Ķ
    0.24
    sembly
    0.24
    &_
    0.24
    梦è§ģ
    0.23
    fony
    0.23
    æŁĶ软
    0.23
    Activations Density 0.401%

    No Known Activations