© 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. 151047
    Prev
    Next
    INDEX
    Explanations

    Mit

    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
    zeros
    -0.29
    _itr
    -0.27
    ihar
    -0.26
    éĽªèĬ±
    -0.25
    ạn
    -0.25
    utters
    -0.25
    大家éĥ½åľ¨
    -0.24
    zza
    -0.24
    .har
    -0.23
    aaaa
    -0.23
    POSITIVE LOGITS
    atory
    0.29
    ician
    0.27
    庶
    0.25
    åīįç½®
    0.25
     dem
    0.25
    amenti
    0.24
    åĢĴ
    0.24
    ÑĤен
    0.24
    ansas
    0.23
    .ensure
    0.23
    Activations Density 1.710%

    No Known Activations