© 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. 142253
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    .ApplyResources
    -0.26
    èį¦
    -0.25
    ãĥ¼ãĥĹ
    -0.25
    ######
    -0.25
    @student
    -0.24
    çĵľ
    -0.24
    į°
    -0.24
    èĬĴæŀľ
    -0.23
    èĽ³
    -0.23
    eah
    -0.23
    POSITIVE LOGITS
     vs
    0.29
    è¹ĩ
    0.27
    VERS
    0.26
    idores
    0.26
    类似
    0.26
     Upper
    0.26
     versus
    0.26
    obi
    0.25
     upper
    0.25
    夺
    0.25
    Activations Density 52.990%

    No Known Activations