© 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. 150703
    Prev
    Next
    INDEX
    Explanations

    Public statements/opinions

    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
    貫
    -0.27
    çĴ°
    -0.25
    ONTAL
    -0.25
    éĵĬ
    -0.25
    导读
    -0.25
    ISTR
    -0.24
    è´¯éĢļ
    -0.24
    贯穿
    -0.24
     Passport
    -0.24
    soever
    -0.24
    POSITIVE LOGITS
     outside
    0.31
     about
    0.30
    çļĩåŃIJ
    0.30
     actively
    0.28
     against
    0.28
     through
    0.28
     directly
    0.27
    lifting
    0.27
     openly
    0.27
     lifting
    0.26
    Activations Density 1.062%

    No Known Activations