© 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. 141643
    Prev
    Next
    INDEX
    Explanations

    even

    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
     contato
    -0.27
    ç½ij讯
    -0.26
     Surely
    -0.26
    vant
    -0.25
    ä½Ļ
    -0.24
    oder
    -0.24
    ÑĭÑħ
    -0.24
     VAN
    -0.24
    ember
    -0.23
    ãģ§ãģĻãĤĪãģŃ
    -0.23
    POSITIVE LOGITS
    æī¹ç¤º
    0.30
     releg
    0.26
     HK
    0.26
    åĩºåı°
    0.25
    =pk
    0.25
    祺
    0.25
     sogar
    0.25
    åĩºåı°äºĨ
    0.24
     подпиÑģ
    0.24
    inded
    0.24
    Activations Density 58.469%

    No Known Activations