© 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. 27-TRANSCODER-HP
    7. 57505
    Prev
    Next
    INDEX
    Explanations

    Even

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīåħ³
    -0.31
    主è¦ģçĶ¨äºİ
    -0.30
    Everything
    -0.29
    åıªæĺ¯
    -0.28
    æ½Ľ
    -0.27
     imaginable
    -0.27
    ä»»ä½ķ人
    -0.26
    缸åħ³åĨħ容
    -0.26
     départ
    -0.26
    æľīä»Ģä¹Ī
    -0.26
    POSITIVE LOGITS
     even
    0.37
    åį³ä½¿æĺ¯
    0.36
    åį³ä½¿
    0.32
    even
    0.31
    -even
    0.30
    uly
    0.30
    åį³ä¾¿æĺ¯
    0.28
    åį³ä¾¿
    0.28
    лев
    0.28
     non
    0.27
    Activations Density 0.007%

    No Known Activations