© 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. 53077
    Prev
    Next
    INDEX
    Explanations

    in

    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
    arp
    -0.25
     Bund
    -0.24
     ValidationError
    -0.23
    Scalars
    -0.23
    oud
    -0.23
    zac
    -0.23
     Dal
    -0.23
     nós
    -0.22
    alent
    -0.22
    ermal
    -0.22
    POSITIVE LOGITS
     a
    0.56
     an
    0.44
    a
    0.43
    "a
    0.35
    -a
    0.35
     ways
    0.35
    _a
    0.33
    )a
    0.32
    'a
    0.32
    åĸľ
    0.31
    Activations Density 0.036%

    No Known Activations