© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30331
    Prev
    Next
    INDEX
    Explanations

    Insufficiency/Negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    otr
    -0.31
    åĬªåĬĽ
    -0.31
    _DL
    -0.29
    æĦıè§ģ
    -0.29
    ETA
    -0.28
    åѵ
    -0.28
    åĽłåľ°
    -0.26
    cca
    -0.26
    çļĦåĬªåĬĽ
    -0.26
    dea
    -0.25
    POSITIVE LOGITS
    çIJĥ
    0.27
     Judicial
    0.25
    ÑģÑĤвеннÑĭе
    0.24
    acking
    0.24
    ||
    0.24
     UserId
    0.23
     Lent
    0.23
     Armour
    0.23
     ê²
    0.23
    è¾¹
    0.23
    Activations Density 3.280%

    No Known Activations