© 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. 63543
    Prev
    Next
    INDEX
    Explanations

    snippets of text

    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
    eken
    -0.31
    çĮ¬
    -0.25
    ehen
    -0.25
    -hit
    -0.25
    èĢĮåİ»
    -0.25
    æĻļ
    -0.24
    ech
    -0.24
    odox
    -0.23
    Indexed
    -0.23
    etto
    -0.23
    POSITIVE LOGITS
    wing
    0.26
    躯
    0.26
    .master
    0.26
     onSave
    0.25
    åij¼
    0.25
    åįķåħĥ
    0.25
    使åij½æĦŁ
    0.24
    master
    0.24
    éŀĺ
    0.24
    åľ¬
    0.23
    Activations Density 68.867%

    No Known Activations