© 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
    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. 102998
    Prev
    Next
    INDEX
    Explanations

    period token

    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
    _rewrite
    -0.06
     //!↵
    -0.06
    いず
    -0.06
    _capability
    -0.06
    קוס
    -0.06
     circuit
    -0.06
     coins
    -0.06
    dfs
    -0.06
     delegate
    -0.06
    县级
    -0.06
    POSITIVE LOGITS
    共计
    0.08
    另一半
    0.07
     specializing
    0.07
    游戏装备
    0.07
    ungkin
    0.06
    旿
    0.06
     lurking
    0.06
    ulti
    0.06
    螱
    0.06
    SpecWarn
    0.06
    Activations Density 0.354%

    No Known Activations