© 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. 24552
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Vu
    -0.25
    _eff
    -0.25
    ám
    -0.25
     nin
    -0.24
     <![
    -0.24
     pitches
    -0.24
    Ljava
    -0.23
    _DEFINED
    -0.23
    avia
    -0.23
    ĵįä½ľ
    -0.23
    POSITIVE LOGITS
    ici
    0.26
    anity
    0.26
    åħ¸
    0.25
    OTA
    0.25
    PM
    0.25
    ful
    0.25
    ado
    0.24
    (pm
    0.24
    .central
    0.24
    çĸ¾
    0.24
    Activations Density 0.001%

    No Known Activations