© 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. 23-TRANSCODER-HP
    7. 24368
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
     cul
    -0.28
    ems
    -0.28
    oure
    -0.28
     balls
    -0.25
     gel
    -0.24
    BarButton
    -0.24
    屡
    -0.24
    ãĥĥãĤ·ãĥ§ãĥ³
    -0.24
    anus
    -0.24
    æľĪæľ«
    -0.23
    POSITIVE LOGITS
     yourselves
    0.34
     yourself
    0.30
    å¯¹ä½ł
    0.29
     yours
    0.28
    欣èµı
    0.28
     your
    0.28
     partial
    0.28
    ä½łåºĶ该
    0.27
     Tears
    0.26
    èģŀãģį
    0.26
    Activations Density 0.006%

    No Known Activations