© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25414
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
    ener
    -0.30
    æİ£
    -0.30
    å¹´ä¹ĭä¹ħ
    -0.27
    ewire
    -0.26
    éĵİ
    -0.25
    -action
    -0.25
    AYS
    -0.24
    BU
    -0.24
    _Generic
    -0.24
    ten
    -0.24
    POSITIVE LOGITS
    åĶ¯ä¸Ģ
    0.89
    æĥŁ
    0.71
    åĶ¯ä¸ĢçļĦ
    0.71
    åĶ¯
    0.68
    åĶ¯æľī
    0.62
     uniquely
    0.56
     unique
    0.56
     única
    0.53
     единÑģÑĤв
    0.51
     only
    0.51
    Activations Density 0.009%

    No Known Activations