© 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. 27-TRANSCODER-HP
    7. 9245
    Prev
    Next
    INDEX
    Explanations

    links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smokers
    -0.30
     Flint
    -0.27
    -sm
    -0.25
    .SM
    -0.25
    çīŁ
    -0.25
    èīº
    -0.24
    					↵					↵
    -0.24
    venta
    -0.24
    ãĤ·ãĥ¼
    -0.24
     Coch
    -0.23
    POSITIVE LOGITS
    ability
    0.28
    anga
    0.27
    than
    0.26
    ips
    0.26
    æĥ³åİ»
    0.25
    ellan
    0.25
    ä¸įä¸Ĭ
    0.25
     favourite
    0.25
    ataire
    0.25
    çī¹å®ļ
    0.25
    Activations Density 0.008%

    No Known Activations