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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 60022
    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_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
    Gay
    -0.08
    巾
    -0.07
    PG
    -0.07
    🆃
    -0.07
    设计
    -0.07
    为之
    -0.07
     continuous
    -0.07
    ;amp
    -0.07
    })();↵↵
    -0.07
    oti
    -0.06
    POSITIVE LOGITS
     angrily
    0.08
     scrollbar
    0.07
    应收
    0.07
     landmark
    0.07
    发现问题
    0.07
     cứu
    0.07
    /channel
    0.07
     miesiąc
    0.07
     accum
    0.07
     scenarios
    0.07
    Activations Density 0.001%

    No Known Activations