© 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. 23740
    Prev
    Next
    INDEX
    Explanations

    that

    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
    uben
    -0.30
    广
    -0.26
    èĢĮéĿŀ
    -0.26
    ison
    -0.25
    cred
    -0.24
    lig
    -0.23
    izon
    -0.23
     rather
    -0.23
    æĺĬ
    -0.23
    uc
    -0.23
    POSITIVE LOGITS
     pá
    0.26
    -peer
    0.26
    Browse
    0.25
    }px
    0.24
    å¤ĦåĪĨ
    0.24
     losses
    0.24
     ind
    0.24
    å¼Ĥåij³
    0.23
     punct
    0.23
     ges
    0.23
    Activations Density 0.007%

    No Known Activations