Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 25667
    Prev
    Next
    INDEX
    Explanations

    texts verses

    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
     pute
    -0.07
     federally
    -0.07
    ᾱ
    -0.07
     Permit
    -0.07
    平均
    -0.07
    DDL
    -0.07
    厉害
    -0.06
    profession
    -0.06
     degrees
    -0.06
    FFFFFF
    -0.06
    POSITIVE LOGITS
     يت
    0.07
    -one
    0.07
    ��드
    0.07
     новый
    0.07
    .gender
    0.06
    っちゃ
    0.06
    /big
    0.06
     לבח
    0.06
    _relation
    0.06
    温情
    0.06
    Activations Density 0.077%

    No Known Activations