© 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. 52974
    Prev
    Next
    INDEX
    Explanations

    number 5, fifty

    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
    occo
    -0.28
    çĿĢ
    -0.28
    ibly
    -0.26
    .program
    -0.25
    INCT
    -0.25
    Folders
    -0.25
     Hammer
    -0.24
    UTION
    -0.24
     Go
    -0.24
    IC
    -0.24
    POSITIVE LOGITS
     Fifty
    0.29
    uar
    0.29
     fifty
    0.27
     gren
    0.27
    ï¼ķ
    0.26
    loon
    0.26
     fünf
    0.26
    5
    0.25
    äºĶåįģ
    0.25
    å°±å¿ħé¡»
    0.24
    Activations Density 0.014%

    No Known Activations