© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 42253
    Prev
    Next
    INDEX
    Explanations

    ica

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >New
    -0.07
    �
    -0.07
    ��
    -0.07
     PRIMARY
    -0.07
    .sz
    -0.07
    },{
    -0.07
    Ֆ
    -0.07
    еть
    -0.06
    프
    -0.06
     ה
    -0.06
    POSITIVE LOGITS
    玘
    0.08
    cipher
    0.07
     pharmaceutical
    0.07
    햔
    0.07
     professionalism
    0.07
     UserRepository
    0.07
     odpowied
    0.07
     möchte
    0.06
    亲
    0.06
    することができます
    0.06
    Activations Density 0.001%

    No Known Activations