© 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. 24829
    Prev
    Next
    INDEX
    Explanations

    names

    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
    _BAL
    -0.25
    ä¸į失
    -0.24
     Prosecutor
    -0.24
     confused
    -0.24
    à¸Ļำ
    -0.24
    æIJ¬
    -0.23
    çĥ¦èºģ
    -0.23
    ITOR
    -0.23
    åĽ´
    -0.23
    ffic
    -0.23
    POSITIVE LOGITS
    ä»ħ代表
    0.26
    åIJIJ
    0.26
    columnName
    0.25
     <<-
    0.25
    alin
    0.25
    èĥĮåIJİçļĦ
    0.24
    rost
    0.24
    ute
    0.24
    kest
    0.23
    ahrenheit
    0.23
    Activations Density 0.001%

    No Known Activations