© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8768
    Prev
    Next
    INDEX
    Explanations

    say mathematical operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    诬
    -0.07
    成龙
    -0.07
    Extensions
    -0.07
     irres
    -0.07
     وإ
    -0.07
    变成
    -0.07
    _GROUP
    -0.07
     anybody
    -0.07
    propri
    -0.07
    .Child
    -0.07
    POSITIVE LOGITS
    })
    0.07
    **)
    0.07
     Datum
    0.07
    )',
    0.07
    })}↵
    0.06
    ][
    0.06
    ])]↵
    0.06
    .bam
    0.06
    طم
    0.06
    ]},
    0.06
    Activations Density 0.012%

    No Known Activations