© 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. 150819
    Prev
    Next
    INDEX
    Explanations

    I

    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
    nish
    -0.31
    Collapse
    -0.28
    ness
    -0.28
    astle
    -0.28
     organisation
    -0.26
    nÃŃ
    -0.26
    elijke
    -0.26
    iele
    -0.26
    ounter
    -0.26
    äge
    -0.25
    POSITIVE LOGITS
    event
    0.31
    ñ
    0.30
    equality
    0.28
    ev
    0.28
    events
    0.27
    Ò£
    0.27
    ções
    0.27
    ober
    0.26
    eu
    0.25
    acob
    0.25
    Activations Density 1.599%

    No Known Activations