© 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. 23214
    Prev
    Next
    INDEX
    Explanations

    memorable/unforgettable

    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
     setSupportActionBar
    -0.29
    OCUS
    -0.27
    -generation
    -0.27
    _INLINE
    -0.26
     Freeze
    -0.24
    ographer
    -0.24
    sst
    -0.24
    elijke
    -0.24
    ÑİÑīей
    -0.24
    chi
    -0.23
    POSITIVE LOGITS
    媾
    0.29
    æľīæĽ´å¥½çļĦ
    0.28
    isel
    0.28
    è¾ij
    0.25
    Integral
    0.25
    æ¶ī
    0.25
    ago
    0.25
    ä¹°åĪ°
    0.25
    æ½ľåľ¨
    0.24
    æīĵçĿĢ
    0.24
    Activations Density 0.007%

    No Known Activations