© 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. 54213
    Prev
    Next
    INDEX
    Explanations

    say "ously"

    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
    acy
    -0.33
    IENT
    -0.33
    ration
    -0.30
    alion
    -0.29
    ERV
    -0.29
    iento
    -0.27
    MENT
    -0.27
    aly
    -0.27
    dent
    -0.26
     Stat
    -0.26
    POSITIVE LOGITS
    çīĪ
    0.27
    omens
    0.26
    psc
    0.26
    çĮ·
    0.26
     compass
    0.25
    cons
    0.24
     heavily
    0.24
    opoulos
    0.23
    讲究
    0.23
     admir
    0.23
    Activations Density 0.019%

    No Known Activations