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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 102788
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _mutex
    -0.08
    TU
    -0.07
    中
    -0.06
     entails
    -0.06
    tc
    -0.06
    وار
    -0.06
    指示
    -0.06
    RESULTS
    -0.06
    {l
    -0.06
    pad
    -0.06
    POSITIVE LOGITS
    }"↵
    0.07
    :relative
    0.07
     ];
↵
    0.07
    ᠨ
    0.07
    },
↵
    0.07
    "};
↵
    0.07
    头痛
    0.07
     preserved
    0.07
     Scottish
    0.06
    },↵↵
    0.06
    Activations Density 0.218%

    No Known Activations