© 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. 91860
    Prev
    Next
    INDEX
    Explanations

    metal

    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
     techno
    -0.07
     عنها
    -0.07
    しています
    -0.07
     Religious
    -0.07
    的历史
    -0.07
     Sanford
    -0.07
     bied
    -0.07
     enrich
    -0.06
     dfs
    -0.06
    rów
    -0.06
    POSITIVE LOGITS
    惺
    0.08
    下面是小
    0.08
    .rectangle
    0.07
    Good
    0.07
    big
    0.07
    랏
    0.07
     things
    0.07
     cup
    0.07
    	perror
    0.07
    Fig
    0.07
    Activations Density 0.169%

    No Known Activations