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. 23-RESID-POST-AA
    6. 131038
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这些问题
    -0.07
                                    ↵
    -0.07
     observed
    -0.07
    .That
    -0.07
    让我们
    -0.07
     wondering
    -0.07
    Lewis
    -0.07
     Participants
    -0.07
     Wyn
    -0.07
    泰州
    -0.06
    POSITIVE LOGITS
    /O
    0.07
     ê
    0.07
    惑
    0.07
     softly
    0.07
    review
    0.07
    メンバー
    0.07
    eof
    0.07
    茴
    0.07
     juni
    0.07
     Songs
    0.07
    Activations Density 0.047%

    No Known Activations