© 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. 24-TRANSCODER-HP
    7. 149276
    Prev
    Next
    INDEX
    Explanations

    say "$"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĤем
    -0.31
    zen
    -0.28
    ctest
    -0.27
    ves
    -0.27
    æŃ¤äºº
    -0.26
    odian
    -0.26
    apter
    -0.26
    arty
    -0.26
    à¹īว
    -0.26
     sabot
    -0.25
    POSITIVE LOGITS
    icularly
    0.26
    触
    0.26
    åĬ³
    0.26
    ä¸įè§ģäºĨ
    0.25
    å°ļ
    0.25
     youth
    0.25
     U
    0.24
    sWith
    0.24
    åĭķãģį
    0.23
    骨
    0.23
    Activations Density 0.178%

    No Known Activations