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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 38277
    Prev
    Next
    INDEX
    Explanations

    так

    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
    .]↵↵
    -0.07
    ):↵↵
    -0.07
    ]↵↵
    -0.07
     capacities
    -0.07
    _CATEGORY
    -0.07
    耳边
    -0.07
    .day
    -0.06
    ἠ
    -0.06
     Aer
    -0.06
     ısı
    -0.06
    POSITIVE LOGITS
     את
    0.08
     الخلي
    0.07
    하자
    0.07
    _preference
    0.07
    衄
    0.07
     Plaint
    0.07
     appellant
    0.07
    [counter
    0.07
    增值
    0.07
    几十
    0.07
    Activations Density 0.002%

    No Known Activations