© 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. 129842
    Prev
    Next
    INDEX
    Explanations

    Questions or instructions

    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
    forge
    -0.31
    çĩ§
    -0.26
    æĮ¯åħ´
    -0.26
    åĽ½åĬ¡
    -0.26
    _FA
    -0.25
    emet
    -0.25
    åIJĥä»Ģä¹Ī
    -0.25
    FLAG
    -0.24
    agra
    -0.24
     wsz
    -0.24
    POSITIVE LOGITS
    andal
    0.33
    ç½ijå°ıç¼ĸ
    0.26
    yal
    0.26
    å®Ŀè´Ŀ
    0.25
     resent
    0.25
    æĦıå¤ĸ
    0.24
    phon
    0.24
     payment
    0.24
    ТÐŀ
    0.23
    ung
    0.23
    Activations Density 2.775%

    No Known Activations