© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161745
    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
    apus
    -0.33
    ceu
    -0.30
    éķĤ
    -0.27
    ocr
    -0.26
    uc
    -0.26
    éĤ®ç®±
    -0.24
    å¾Īä¹ħ
    -0.24
     {}.
    -0.24
    å»
    -0.24
    èĢĻ
    -0.24
    POSITIVE LOGITS
     prima
    0.29
    å¢ĥ
    0.26
    å®°
    0.25
    addock
    0.25
     portions
    0.24
    ción
    0.24
    Wolf
    0.24
    ä¼°
    0.24
    åĩ¡æĺ¯
    0.23
    |#
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.