© 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. 130664
    Prev
    Next
    INDEX
    Explanations

    overcoming challenges

    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
    æ´ĭ
    -0.31
     }};↵
    -0.30
     coats
    -0.27
    çĶŁçī©åѦ
    -0.26
     Coat
    -0.26
    Ĥæķ°
    -0.25
    ;};↵
    -0.24
    åĿļæĮģ以
    -0.24
    ãĥ¼ãĥī
    -0.24
     Initial
    -0.23
    POSITIVE LOGITS
    çģµæĦŁ
    0.30
    orque
    0.28
     ray
    0.27
    or
    0.27
     transparent
    0.26
     Matth
    0.25
     reason
    0.24
     buck
    0.24
    -sdk
    0.24
    ***
    0.24
    Activations Density 15.554%

    No Known Activations