© 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. 19-TRANSCODER-HP
    7. 6054
    Prev
    Next
    INDEX
    Explanations

    Descriptive, informational, historical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    against
    -0.28
    ToOne
    -0.28
    æ³¢çī¹
    -0.27
     endIndex
    -0.26
    ç¬ij声
    -0.26
    pecial
    -0.24
    -gradient
    -0.24
     against
    -0.23
    Break
    -0.23
    >Password
    -0.23
    POSITIVE LOGITS
     earliest
    0.41
    æŶéĹ´
    0.37
    æľĢæĹ©
    0.36
     oldest
    0.33
    æľĢæĹ©çļĦ
    0.33
    æĹ©åľ¨
    0.32
     early
    0.31
    éģĹçķĻ
    0.30
     older
    0.30
    å°½æĹ©
    0.30
    Activations Density 0.372%

    No Known Activations