© 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. 30-TRANSCODER-HP
    7. 95440
    Prev
    Next
    INDEX
    Explanations

    Medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dig
    -0.30
    dig
    -0.29
    _digest
    -0.29
     flag
    -0.28
    Clr
    -0.27
     Lands
    -0.27
    ãģĺ
    -0.27
    Dig
    -0.27
    gent
    -0.27
     target
    -0.27
    POSITIVE LOGITS
    ION
    0.30
    ioni
    0.29
    ortion
    0.29
    åµĮ
    0.28
     reg
    0.28
    ered
    0.27
    ions
    0.27
    ion
    0.27
     redraw
    0.26
    InSection
    0.26
    Activations Density 0.108%

    No Known Activations