© 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 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. 15-RESID-POST-AA
    11. 118250
    Prev
    Next
    INDEX
    Explanations

    code/random snippets

    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
     قد
    -0.07
    	RTCK
    -0.07
    祧
    -0.06
    اصر
    -0.06
    ᐖ
    -0.06
    𐎹
    -0.06
    -confidence
    -0.06
    مسئول
    -0.06
    .getOwnPropertyDescriptor
    -0.06
    RunLoop
    -0.06
    POSITIVE LOGITS
    .↵
    0.12
    ↵
    0.12
    1
    0.11
    。↵
    0.11
    ↵↵
    0.10
    .↵↵
    0.10
    ↵
    0.10
    的
    0.09
     is
    0.09
    )↵
    0.08
    Activations Density 1.345%

    No Known Activations