© 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. 25622
    Prev
    Next
    INDEX
    Explanations

    code/licenses

    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
    åģļæ³ķ
    -0.26
    pery
    -0.25
    ÑĢей
    -0.25
    ographer
    -0.24
    ä¸Ńæľī
    -0.24
    å¾ģä¿¡
    -0.24
    ÑĨиÑĤ
    -0.24
    åıijçĥŃ
    -0.23
    íĬ¼
    -0.23
    enna
    -0.23
    POSITIVE LOGITS
    åĪĩæĸŃ
    0.28
    æĶ¾åĩº
    0.26
    erring
    0.26
    æĶ¹æŃ£
    0.25
    åĢĴéĹŃ
    0.25
    opsis
    0.25
    ä»
    0.24
     fled
    0.24
     fic
    0.24
    dac
    0.24
    Activations Density 0.001%

    No Known Activations