© 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. 33-TRANSCODER-HP
    7. 52961
    Prev
    Next
    INDEX
    Explanations

    broad factual knowledge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exclusive
    -0.30
     exclus
    -0.30
    ecz
    -0.28
    Exclusive
    -0.27
    etimes
    -0.27
    ective
    -0.27
    ettes
    -0.26
    -exclusive
    -0.26
    iquement
    -0.26
    ssi
    -0.26
    POSITIVE LOGITS
    è¯įæĿ¡
    0.30
    èĴĻ
    0.28
     grain
    0.27
    bcrypt
    0.26
    ä¼ij
    0.26
    åįłæľī
    0.25
    ut
    0.25
    æĮĩ
    0.25
     Faker
    0.25
     vein
    0.24
    Activations Density 0.016%

    No Known Activations