© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30570
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <head
    -0.07
    👘
    -0.07
    	pos
    -0.07
     unbiased
    -0.06
    枉
    -0.06
    ㉯
    -0.06
    .abspath
    -0.06
    devil
    -0.06
    莠
    -0.06
    .openg
    -0.06
    POSITIVE LOGITS
     rumours
    0.08
    lua
    0.07
    ệnh
    0.07
     صحيح
    0.07
    _SER
    0.06
    )}.
    0.06
    .records
    0.06
    רכי
    0.06
    checks
    0.06
    られます
    0.06
    Activations Density 0.031%

    No Known Activations