© 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. 150206
    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
    ander
    -0.37
    isel
    -0.30
     trom
    -0.29
    ainer
    -0.27
    iner
    -0.27
    _ros
    -0.26
    Seek
    -0.26
    eer
    -0.26
    (string
    -0.25
    anders
    -0.25
    POSITIVE LOGITS
    ä¼łéĹ»
    0.27
    æ®ĺ
    0.27
    fuse
    0.27
    è¯ı
    0.25
    å¤įä»ĩ
    0.25
    空æ°Ķè´¨éĩı
    0.25
    åľ¨çݩ家
    0.24
    æļĤç¼ĵ
    0.24
    æ®ĭ
    0.24
    ä½łè§īå¾Ĺ
    0.24
    Activations Density 1.442%

    No Known Activations

    This feature has no known activations.