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. 15-RESID-POST-AA
    6. 14190
    Prev
    Next
    INDEX
    Explanations

    HTML

    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
     Wh
    -0.07
    成都市
    -0.07
    }_{
    -0.07
    日
    -0.06
     homes
    -0.06
     secondary
    -0.06
    具有
    -0.06
    _pickle
    -0.06
    ạnh
    -0.06
    imension
    -0.06
    POSITIVE LOGITS
     Typ
    0.07
     italian
    0.07
    given
    0.07
    分布式
    0.07
    迁移
    0.07
    REV
    0.07
    	E
    0.07
    族自治
    0.07
    srv
    0.07
     GPL
    0.07
    Activations Density 0.039%

    No Known Activations