© 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. 141679
    Prev
    Next
    INDEX
    Explanations

    cash

    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
    åľ¨éĤ£éĩĮ
    -0.28
    æijĨæĶ¾
    -0.28
    éĤ£äºĽ
    -0.26
    主è¦ģä»İäºĭ
    -0.25
    .poly
    -0.25
    åİŁåĪĻ
    -0.25
    åİŁåīĩ
    -0.25
    èĢĺ
    -0.24
    rees
    -0.24
     principle
    -0.24
    POSITIVE LOGITS
    ilig
    0.30
    ılm
    0.27
    ä¼ļéķ¿
    0.26
    iento
    0.25
    æľī幸
    0.25
    ä¸ĩå¤ļ
    0.25
    NAMESPACE
    0.24
    ière
    0.24
    å§Ķ
    0.24
    erp
    0.23
    Activations Density 5.507%

    No Known Activations