© 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. 149811
    Prev
    Next
    INDEX
    Explanations

    &

    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
     however
    -0.29
    however
    -0.28
    @show
    -0.27
    ular
    -0.26
    iane
    -0.25
    arius
    -0.24
    @Id
    -0.24
    /or
    -0.23
     detailed
    -0.23
     Dane
    -0.23
    POSITIVE LOGITS
    amp
    0.52
    AMP
    0.38
    nbsp
    0.37
    quot
    0.36
     amp
    0.33
    raquo
    0.31
    åıĪèĥ½
    0.29
    atri
    0.28
    lt
    0.27
    ampus
    0.27
    Activations Density 1.525%

    No Known Activations