© 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. 107038
    Prev
    Next
    INDEX
    Explanations

    public locations / events

    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
    Ind
    -0.27
     hydr
    -0.26
     Ind
    -0.26
    è´¨éĩıåĴĮ
    -0.26
     Indigenous
    -0.26
     Learned
    -0.25
    Ø®ÙĦÙģ
    -0.25
    ÐľÐIJ
    -0.24
    (chart
    -0.24
    aria
    -0.24
    POSITIVE LOGITS
    Evt
    0.26
     melee
    0.26
     egt
    0.25
    俸
    0.24
    å¾ĢåIJİ
    0.24
    ä½Ĩ她
    0.24
     uns
    0.24
    oseconds
    0.24
    为æĬĵ
    0.23
    è¿ĩå¾Ģ
    0.23
    Activations Density 5.757%

    No Known Activations