© 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. 25043
    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
     permanent
    -0.29
     Baker
    -0.29
     Permanent
    -0.28
     Best
    -0.27
    éĥİ
    -0.27
    æ°¸ä¹ħ
    -0.26
     Rede
    -0.25
    Permanent
    -0.25
     Overse
    -0.25
    ä¿¡è´·
    -0.25
    POSITIVE LOGITS
    variant
    0.27
    regar
    0.26
    对çħ§
    0.26
    =sys
    0.26
    least
    0.25
    çĶ©
    0.25
    adero
    0.24
    è¶ĬæĿ¥
    0.24
    ffield
    0.24
    åıįæŃ£
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.