© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 52446
    Prev
    Next
    INDEX
    Explanations

    mechanism of action

    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
    jk
    -0.07
    Concept
    -0.07
     DEVELO
    -0.07
    设计
    -0.07
    なぁ
    -0.07
    .sdk
    -0.07
    련
    -0.07
     collide
    -0.07
    ってしまった
    -0.06
    izzer
    -0.06
    POSITIVE LOGITS
    (outputs
    0.08
     subtract
    0.07
    深深
    0.07
     emailAddress
    0.07
     \/
    0.07
    ul
    0.07
    =\"$
    0.07
    px
    0.06
     \"%
    0.06
    .Extension
    0.06
    Activations Density 0.027%

    No Known Activations