© 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. 107741
    Prev
    Next
    INDEX
    Explanations

    months

    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
    mount
    -0.25
    als
    -0.25
    ucose
    -0.24
    襦
    -0.24
    èºģ
    -0.23
    ource
    -0.23
    łéĻ¤
    -0.23
    éĦĻ
    -0.23
    rex
    -0.23
    alc
    -0.23
    POSITIVE LOGITS
    enna
    0.29
     wah
    0.28
    å¸Ī
    0.27
     boyc
    0.24
     ens
    0.24
    æĢ»çIJĨ
    0.24
     setback
    0.24
     challenger
    0.23
    ãģ¤ãģĭ
    0.23
    èĢģå¸ĪçļĦ
    0.23
    Activations Density 20.940%

    No Known Activations