© 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. 142020
    Prev
    Next
    INDEX
    Explanations

    company names

    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
    NR
    -0.29
    IVA
    -0.26
    Seen
    -0.26
    _NR
    -0.25
     NR
    -0.25
     antis
    -0.25
    nte
    -0.25
    ãĥ¼ãĥī
    -0.24
    &R
    -0.24
    imeters
    -0.24
    POSITIVE LOGITS
    onz
    0.27
    åı©
    0.25
    è§Ĥ念
    0.25
     opin
    0.24
    åħ¬äº¤
    0.23
    éĢļè¯Ŀ
    0.23
     pik
    0.23
    Unless
    0.23
    äºĭåħ³
    0.23
    ->{$
    0.23
    Activations Density 12.161%

    No Known Activations