© 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. 15-RESID-POST-AA
    11. 84914
    Prev
    Next
    INDEX
    Explanations

    spices and mixes

    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
    rait
    -0.08
     pencil
    -0.07
    uvw
    -0.07
    ืน
    -0.07
    życz
    -0.07
    igrant
    -0.07
    istence
    -0.06
    izarre
    -0.06
    [num
    -0.06
     GUIStyle
    -0.06
    POSITIVE LOGITS
    联动
    0.07
    还会
    0.07
     breaches
    0.07
    heim
    0.07
     schematic
    0.07
    brand
    0.07
    }"↵↵
    0.07
     antibodies
    0.07
     ax
    0.07
    per
    0.06
    Activations Density 0.100%

    No Known Activations