© 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. 150643
    Prev
    Next
    INDEX
    Explanations

    Code snippets and foreign characters

    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
    caf
    -0.28
    /accounts
    -0.27
    çķĪ
    -0.26
    orama
    -0.26
    genes
    -0.25
    scriptId
    -0.25
    жи
    -0.24
    ollo
    -0.23
     enf
    -0.23
    orth
    -0.23
    POSITIVE LOGITS
    è¿ľå¤Ħ
    0.31
    æĮij
    0.31
    è¿ľæĸ¹
    0.27
     Sau
    0.27
    éĢīæĭ
    0.25
     ÐŁÐ¾Ñĩ
    0.25
    å°ijæķ°
    0.24
     calculations
    0.24
    Âł
    0.24
    ier
    0.24
    Activations Density 0.111%

    No Known Activations