© 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. 130382
    Prev
    Next
    INDEX
    Explanations

    it

    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
    è½®
    -0.27
     Clyde
    -0.27
    èĥĮéĿ¢
    -0.26
    輪
    -0.25
    itime
    -0.25
    lish
    -0.24
    ì¹ĺ
    -0.24
    -case
    -0.23
     purchaser
    -0.23
    losure
    -0.23
    POSITIVE LOGITS
    arb
    0.29
    @s
    0.28
     sug
    0.28
     Experiment
    0.26
    çĶŁæ´»çݯå¢ĥ
    0.26
    _MAKE
    0.26
    使ä¹ĭ
    0.25
    кÑĢÑĥÑĤ
    0.25
    Experiment
    0.25
    åĨ³
    0.24
    Activations Density 24.529%

    No Known Activations