© 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. 150989
    Prev
    Next
    INDEX
    Explanations

    science and methodologies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    and
    -0.36
    åĴĮæĶ¯æĮģ
    -0.35
     and
    -0.34
    åĴĮæĬĢæľ¯
    -0.33
    æĢ§åĴĮ
    -0.33
     vÃł
    -0.31
    åĴĮ
    -0.30
    並å°ĩ
    -0.29
     и
    -0.29
    并å°Ĩ
    -0.27
    POSITIVE LOGITS
    åı¸
    0.29
    ÑĢов
    0.27
    èĩªçĦ¶
    0.26
    æīĵ
    0.26
    LOB
    0.25
    oded
    0.25
    缮åħī
    0.24
     characterize
    0.24
    缮ãģ«
    0.24
    tree
    0.23
    Activations Density 0.269%

    No Known Activations