© 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. 22950
    Prev
    Next
    INDEX
    Explanations

    Charleston

    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
    angen
    -0.27
    userdata
    -0.26
    åıijå±ķ空éĹ´
    -0.25
    çĤ·
    -0.25
    kick
    -0.25
     rewind
    -0.24
    çľĭæ³ķ
    -0.24
    striction
    -0.24
    pir
    -0.23
    éħ
    -0.23
    POSITIVE LOGITS
    å®Ī
    0.28
    	operator
    0.26
    :".
    0.25
    rosis
    0.25
    nil
    0.25
    ç´łè´¨æķĻèĤ²
    0.25
    âĭĦ
    0.24
    æľĿ
    0.24
     DevExpress
    0.24
    å¤ķ
    0.24
    Activations Density 0.085%

    No Known Activations