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. 24064
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
     mercy
    -0.07
    icking
    -0.07
     showc
    -0.07
    .rec
    -0.07
    ¶
    -0.06
    ticket
    -0.06
    はじ
    -0.06
    recision
    -0.06
    陕西
    -0.06
    YNC
    -0.06
    POSITIVE LOGITS
     deficiencies
    0.07
    gli
    0.07
     '}
    0.07
    енно
    0.07
    /dialog
    0.06
    嘟
    0.06
    颇为
    0.06
    ents
    0.06
    埴
    0.06
    ]&
    0.06
    Activations Density 0.080%

    No Known Activations