© 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. 141603
    Prev
    Next
    INDEX
    Explanations

    Document snippets

    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
    oids
    -0.27
     dele
    -0.27
    oid
    -0.26
     sint
    -0.26
     differ
    -0.24
    chen
    -0.24
    ych
    -0.24
     gratuita
    -0.24
     redundant
    -0.24
    åĨ³å®ļ
    -0.24
    POSITIVE LOGITS
    LAS
    0.28
    åı¸
    0.27
    .aspect
    0.27
    è¥Ħ
    0.27
    åħij
    0.25
     qed
    0.25
    缮åīį为æŃ¢
    0.25
    æīĩ
    0.25
     xúc
    0.25
    genome
    0.24
    Activations Density 0.885%

    No Known Activations