© 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. 149187
    Prev
    Next
    INDEX
    Explanations

    strange words

    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
    åĨł
    -0.29
    æ¸ł
    -0.29
    isd
    -0.28
    ists
    -0.28
     collaborators
    -0.26
    并没æľī
    -0.25
     Laurel
    -0.25
    context
    -0.24
     hypotheses
    -0.24
     affiliates
    -0.24
    POSITIVE LOGITS
    éĩįçĶŁ
    0.26
    idar
    0.26
     @{↵
    0.25
    åı¯èĥ½åıijçĶŁ
    0.25
    CharCode
    0.24
    åijµæĬ¤
    0.24
    åij¨è½¬
    0.24
    _ELEM
    0.23
    uye
    0.23
    icens
    0.23
    Activations Density 0.129%

    No Known Activations