© 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. 162953
    Prev
    Next
    INDEX
    Explanations

    varied, abstract, and complex contexts

    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
    ocker
    -0.33
    éŃħåĬĽ
    -0.28
    ,copy
    -0.26
    asca
    -0.26
    esome
    -0.26
    ODULE
    -0.25
    çĶ·å¥³
    -0.25
    éľ¹
    -0.25
    otoxic
    -0.24
    大æī¹
    -0.24
    POSITIVE LOGITS
     technically
    0.42
    并ä¸įæĺ¯
    0.34
    并没æľī
    0.33
    并ä¸į
    0.32
    ä¸ĢçĤ¹éĥ½ä¸į
    0.32
    å¹¶æľª
    0.32
    ä¸įæĺ¯
    0.31
     isn
    0.31
    並ä¸į
    0.31
    ãģ§ãģ¯ãģĤãĤĬãģ¾ãģĽãĤĵ
    0.29
    Activations Density 0.002%

    No Known Activations