© 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. 151020
    Prev
    Next
    INDEX
    Explanations

    code, forum questions

    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
     itself
    -0.25
    ç¼Ī
    -0.25
    acies
    -0.25
    ACY
    -0.24
    è¶ĭåĬ¿
    -0.24
     annonces
    -0.24
    æĬĺ
    -0.24
    iere
    -0.24
     SharedModule
    -0.23
    -fluid
    -0.23
    POSITIVE LOGITS
    pii
    0.26
    ç»Ļ
    0.26
    æīĵæĸŃ
    0.26
    etus
    0.25
    itat
    0.25
    iste
    0.25
    olls
    0.24
    ipa
    0.24
    force
    0.24
    otive
    0.24
    Activations Density 0.825%

    No Known Activations