© 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. 129456
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èı©æıIJ
    -0.24
    æ´²
    -0.24
    IDL
    -0.24
    associate
    -0.24
    anda
    -0.24
    ype
    -0.24
    bindings
    -0.24
    onn
    -0.23
    asan
    -0.23
    occus
    -0.23
    POSITIVE LOGITS
    缮
    0.29
    Īëĭ¤
    0.28
     clearColor
    0.27
    å¿Ĺ
    0.26
    åı£
    0.26
    容
    0.25
    æ®ĭçķĻ
    0.25
    ichtig
    0.25
    å½Ĵ
    0.25
     **)
    0.24
    Activations Density 1.958%

    No Known Activations

    This feature has no known activations.