© 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. 20-TRANSCODER-HP
    7. 141186
    Prev
    Next
    INDEX
    Explanations

    invitations/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŁIJ个
    -0.28
    æŁIJ
    -0.28
    åĤ¬
    -0.27
     sack
    -0.26
    /lists
    -0.25
    èĥĻ
    -0.25
    clearfix
    -0.25
    å¡ij
    -0.24
    an
    -0.24
     polite
    -0.24
    POSITIVE LOGITS
    tring
    0.28
    _='
    0.25
    éĢ
    0.25
    !='
    0.25
    //:
    0.25
    ¹
    0.25
    ltk
    0.24
    ndef
    0.23
     ['/
    0.23
    ï¼ģãĢį
    0.23
    Activations Density 10.968%

    No Known Activations