© 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. 63023
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    abis
    -0.27
    å§IJ妹
    -0.26
    Exact
    -0.26
     thereafter
    -0.24
     Exact
    -0.24
    åľ¨éĤ£éĩĮ
    -0.24
     incons
    -0.24
    俦
    -0.23
     expl
    -0.23
    oken
    -0.23
    POSITIVE LOGITS
    åĪĨå¸ĥåľ¨
    0.45
    åŃĺåľ¨äºİ
    0.41
    ä½įäºİ
    0.41
    åıijçĶŁåľ¨
    0.41
    åĩºçİ°åľ¨
    0.39
    æĶ¾åľ¨
    0.38
    éĽĨä¸Ńåľ¨
    0.35
    èģĮä¸ļ
    0.32
     located
    0.31
    çĶŁäºİ
    0.31
    Activations Density 86.462%

    No Known Activations