© 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. 12-TRANSCODER-HP
    7. 23040
    Prev
    Next
    INDEX
    Explanations

    animal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŃĶåį·
    -0.30
    Tag
    -0.28
    _tag
    -0.28
    bage
    -0.27
    交代
    -0.27
    ving
    -0.26
    tag
    -0.25
     GENERATED
    -0.25
    Tags
    -0.25
    æ´»çĿĢ
    -0.25
    POSITIVE LOGITS
    åľ°ä¸Ĭ
    0.30
    oreal
    0.28
     real
    0.25
    ä¸įå½ĵ
    0.25
    Contain
    0.25
    大å°ı
    0.24
    emodel
    0.24
     REAL
    0.24
     tend
    0.24
     absentee
    0.24
    Activations Density 0.005%

    No Known Activations