© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 2154
    Prev
    Next
    INDEX
    Explanations

    ly

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nota
    -0.07
    quia
    -0.07
    ای
    -0.07
     declined
    -0.07
    .Word
    -0.07
     maior
    -0.06
    acl
    -0.06
    taskId
    -0.06
    続
    -0.06
     makes
    -0.06
    POSITIVE LOGITS
    _SRC
    0.07
    事后
    0.07
    quares
    0.07
     qed
    0.06
     brand
    0.06
    TRGL
    0.06
     cutoff
    0.06
    ⊳
    0.06
    晚年
    0.06
     Operations
    0.06
    Activations Density 0.008%

    No Known Activations