© 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. 53115
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    ar
    -0.50
     ar
    -0.48
    .ar
    -0.41
    аÑĢ
    -0.41
    _ar
    -0.41
    	ar
    -0.41
    -ar
    -0.40
    AR
    -0.39
    Ar
    -0.38
    arch
    -0.38
    POSITIVE LOGITS
    agara
    0.25
    affer
    0.25
     eternity
    0.24
    neas
    0.24
    aget
    0.24
     heterosexual
    0.23
    ]|[
    0.23
     FAG
    0.23
     Rape
    0.23
    stå
    0.23
    Activations Density 0.147%

    No Known Activations