© 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. 15-RESID-POST-AA
    6. 123724
    Prev
    Next
    INDEX
    Explanations

    and,

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }.
    -0.07
     DisplayName
    -0.07
    _person
    -0.07
    _similarity
    -0.07
     breathing
    -0.07
    _via
    -0.07
    ,re
    -0.07
    CCCC
    -0.07
     []*
    -0.07
    _ON
    -0.07
    POSITIVE LOGITS
    markers
    0.08
    际
    0.07
    ente
    0.07
    有价值的
    0.07
    مرا
    0.07
    מדי
    0.07
    켯
    0.06
    lands
    0.06
    imate
    0.06
    sk
    0.06
    Activations Density 0.017%

    No Known Activations