© 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. 24-TRANSCODER-HP
    7. 149880
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłçĸij
    -0.30
    /sm
    -0.30
    åĴ³
    -0.27
    dı
    -0.27
    Äħ
    -0.26
    å¼ĥ
    -0.25
    RECT
    -0.25
    ä¸ī次
    -0.24
    WK
    -0.24
     retained
    -0.24
    POSITIVE LOGITS
    _ER
    0.26
     evolved
    0.25
    LEN
    0.24
     plur
    0.24
     shortage
    0.24
    èģĬèģĬ
    0.23
    èī¯
    0.23
    æŃ£è§Ħ
    0.23
     Label
    0.23
    ibi
    0.23
    Activations Density 0.106%

    No Known Activations

    This feature has no known activations.