© 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. 141385
    Prev
    Next
    INDEX
    Explanations

    why

    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
    æ²»çĸĹæĸ¹æ³ķ
    -0.27
    viders
    -0.25
     shift
    -0.24
    å®ļäºĨ
    -0.24
    Dat
    -0.24
    åįķ项
    -0.24
    limitations
    -0.24
     caut
    -0.24
    uale
    -0.23
     "]
    -0.23
    POSITIVE LOGITS
    rei
    0.26
    AsStream
    0.26
    èµļéĴ±
    0.25
    izador
    0.25
    æĪ²
    0.24
    vos
    0.23
    arine
    0.23
    ernes
    0.23
    jong
    0.23
    ä¸ĩä½Ļåħĥ
    0.23
    Activations Density 6.318%

    No Known Activations