© 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. 150367
    Prev
    Next
    INDEX
    Explanations

    seed

    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
    íĦ°
    -0.27
     intercept
    -0.27
    interest
    -0.27
    åıijå±ķ
    -0.26
     interest
    -0.26
    install
    -0.26
    év
    -0.25
     ná»ģn
    -0.25
    inter
    -0.25
    develop
    -0.25
    POSITIVE LOGITS
    ling
    0.30
    lings
    0.29
     buck
    0.28
    èįļ
    0.27
    çĤ¹å¤ļ
    0.26
    iated
    0.24
    erness
    0.24
    /provider
    0.24
    iosa
    0.24
    æ·ĸ
    0.24
    Activations Density 0.954%

    No Known Activations