© 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. 24101
    Prev
    Next
    INDEX
    Explanations

    Instructions / Documentation

    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
    gart
    -0.28
    izer
    -0.27
    asan
    -0.25
    çĭŃçªĦ
    -0.25
    ICES
    -0.24
     IMPLIED
    -0.24
    æĭ½
    -0.24
    izado
    -0.24
    æݨ
    -0.24
    CreateDate
    -0.24
    POSITIVE LOGITS
    éĢĤçĶ¨äºİ
    0.31
     adequately
    0.29
     suitable
    0.29
    åºĶåıĬæŶ
    0.29
    éĢĤåIJĪ
    0.29
    å©·
    0.28
     spir
    0.27
    ãĥĪãĥ«
    0.27
    åı¯çĶ¨äºİ
    0.27
    CTR
    0.27
    Activations Density 0.002%

    No Known Activations