© 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. 107423
    Prev
    Next
    INDEX
    Explanations

    of

    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
    åĪĨè¡Į
    -0.27
    èĢĥèĻij
    -0.25
    使åij½æĦŁ
    -0.25
    cheduler
    -0.25
    Destroy
    -0.24
    èĢĥèĻijåĪ°
    -0.23
    Mine
    -0.23
    è´·
    -0.23
    ĺ认
    -0.23
    强度
    -0.22
    POSITIVE LOGITS
    rat
    0.27
    zew
    0.26
    åħ¶ä»ĸ人
    0.26
     simply
    0.26
     AHL
    0.25
    åĩºåĵģ
    0.25
     sc
    0.24
     extended
    0.24
     Cou
    0.24
    elas
    0.24
    Activations Density 4.630%

    No Known Activations