© 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. 4909
    Prev
    Next
    INDEX
    Explanations

    Technical questions/documentation

    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
    æ²±
    -0.31
     specialised
    -0.27
    presso
    -0.25
    /native
    -0.25
     veto
    -0.25
     shocks
    -0.24
    formance
    -0.24
    férence
    -0.24
    çĦ¶å¾Į
    -0.24
    -checkbox
    -0.23
    POSITIVE LOGITS
     MCS
    0.27
    æĹ¥æĬ¥ç¤¾
    0.27
    ti
    0.27
    åŀĽ
    0.26
    åijĻ
    0.26
    å®°
    0.25
     permalink
    0.25
    æĬ¬
    0.25
    ATS
    0.25
    perse
    0.24
    Activations Density 0.008%

    No Known Activations