© 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. 54261
    Prev
    Next
    INDEX
    Explanations

    noble titles and locations

    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
    isé
    -0.30
    å°ķ
    -0.26
    ven
    -0.26
    anten
    -0.26
    iser
    -0.25
    fffffff
    -0.25
    [child
    -0.24
    _FIN
    -0.24
    izzato
    -0.23
    [input
    -0.23
    POSITIVE LOGITS
     diploma
    0.35
     Diploma
    0.31
    dia
    0.30
     Elect
    0.29
     Wal
    0.27
    åħįéĻ¤
    0.27
    shot
    0.27
     Imperial
    0.27
    å¾·å°Ķ
    0.26
     Wells
    0.25
    Activations Density 0.014%

    No Known Activations