© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162982
    Prev
    Next
    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽł
    -0.29
    åŁ¹èĤ²
    -0.27
    åĽłç´ł
    -0.25
    .Mutable
    -0.25
     doch
    -0.23
    åĨ³å®ļäºĨ
    -0.23
    缸äºĴ
    -0.23
    æĿijåŃIJ
    -0.23
     aggi
    -0.23
    ë²
    -0.23
    POSITIVE LOGITS
    niest
    0.28
    .native
    0.28
     example
    0.27
    åĥļ
    0.27
    gings
    0.26
    ãģ¤
    0.25
    inz
    0.25
    Slash
    0.25
     scale
    0.25
     perhaps
    0.24
    Activations Density 0.011%

    No Known Activations