© 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. 149556
    Prev
    Next
    INDEX
    Explanations

    advice

    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
    æ¯ı次éĥ½
    -0.29
    æķijæµİ
    -0.27
    æĽĻ
    -0.27
    åİŁæĿ¥æĺ¯
    -0.26
    对çĿĢ
    -0.24
    metic
    -0.24
    mez
    -0.24
    anmar
    -0.24
    (chan
    -0.24
    åī©
    -0.24
    POSITIVE LOGITS
     gathered
    0.27
    åĽĬ
    0.26
     choices
    0.26
     qualified
    0.26
    omon
    0.25
     counsel
    0.25
    gather
    0.25
    ä½ĵåĬĽ
    0.24
     Choices
    0.24
    赶
    0.24
    Activations Density 0.668%

    No Known Activations