© 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. 25217
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æµ´
    -0.30
     Cookbook
    -0.28
    replacement
    -0.26
     cookbook
    -0.26
     molec
    -0.25
     smell
    -0.25
     replacement
    -0.25
     resort
    -0.24
    eldom
    -0.24
    PasswordField
    -0.24
    POSITIVE LOGITS
    ä½łæĺ¯
    0.29
    ä»Ģä¹ĪæŶåĢĻ
    0.28
    éĽĨä¸Ń
    0.27
    ehen
    0.27
    ä½ķæŶ
    0.25
    fen
    0.25
    ä¸Ģå®ļ
    0.24
    çĬ¶
    0.24
    å±Ĥ次
    0.24
    åİļ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.