© 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. 32-TRANSCODER-HP
    7. 41411
    Prev
    Next
    INDEX
    Explanations

    points

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     far
    -1.44
    far
    -1.22
    Far
    -1.05
     Far
    -1.05
    è¿ľ
    -1.01
     FAR
    -0.98
    _far
    -0.94
    è¿ľè¿ľ
    -0.85
    éģł
    -0.77
    _FAR
    -0.68
    POSITIVE LOGITS
     adjacent
    0.31
     Adj
    0.26
    Adjacent
    0.26
    adj
    0.26
    éĤ»
    0.25
     Crafts
    0.25
    arme
    0.25
     adj
    0.25
    è¹Ń
    0.25
    æĥ°
    0.24
    Activations Density 0.002%

    No Known Activations