© 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. 24401
    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
    æ¶ī
    -0.30
    ram
    -0.26
    å¡Ķ
    -0.26
    bre
    -0.25
    à¹Ģà¸Ĭ
    -0.25
    ub
    -0.25
    æŀ³
    -0.24
     bre
    -0.24
    éĢŁ
    -0.24
    ÙĨز
    -0.24
    POSITIVE LOGITS
    举è¡ĮçļĦ
    0.27
    é¹ĥ
    0.26
    âĻª↵↵
    0.25
    ellation
    0.25
     emerging
    0.25
    [out
    0.24
    essenger
    0.24
    éĢĻ次
    0.24
    ведение
    0.24
    ç»Ħç»ĩå¼Ģå±ķ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.