© 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. 22-TRANSCODER-HP
    7. 129468
    Prev
    Next
    INDEX
    Explanations

    bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AFF
    -0.27
    ä¸ĩ亩
    -0.27
    	except
    -0.26
    except
    -0.25
    eyes
    -0.25
    害
    -0.25
     Schultz
    -0.24
    brand
    -0.24
     outright
    -0.24
    asz
    -0.24
    POSITIVE LOGITS
    InitialState
    0.31
    ä¸įè¦ģ太
    0.28
    å¿ĥå¢ĥ
    0.27
    人家
    0.26
    ernals
    0.25
    æ¿ĢçĥĪçļĦ
    0.25
    èĴĮ
    0.24
    è·³åĩº
    0.24
    (--
    0.24
    lama
    0.23
    Activations Density 0.060%

    No Known Activations