© 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. 22758
    Prev
    Next
    INDEX
    Explanations

    and

    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
    (sv
    -0.30
     mel
    -0.29
    (END
    -0.26
    ijn
    -0.25
    Mel
    -0.25
     паÑĢÑĤ
    -0.24
    ndx
    -0.24
    anches
    -0.24
    å°±è§īå¾Ĺ
    -0.24
     END
    -0.24
    POSITIVE LOGITS
     grate
    0.29
    uire
    0.27
    è£ĺ
    0.27
    åıªä¸º
    0.25
    dition
    0.24
    è¿İ
    0.24
     division
    0.24
     neg
    0.24
     Rai
    0.24
     di
    0.23
    Activations Density 0.006%

    No Known Activations