© 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. 150484
    Prev
    Next
    INDEX
    Explanations

    cos

    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
    æĪªèĩ³
    -0.26
    -da
    -0.26
    (Project
    -0.25
     marches
    -0.24
    igin
    -0.24
    Dep
    -0.24
    HEET
    -0.24
    æĶĺ
    -0.24
    .getB
    -0.23
    èĩªçĦ¶
    -0.23
    POSITIVE LOGITS
    èľ
    0.28
    Fraction
    0.28
    fraction
    0.27
     Fraction
    0.26
     sight
    0.26
     Opport
    0.26
     //~
    0.25
     fraction
    0.25
     fractional
    0.25
    é¼
    0.25
    Activations Density 0.183%

    No Known Activations