© 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. 11-RESID-POST-AA
    11. 29484
    Prev
    Next
    INDEX
    Explanations

    complex sentences

    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
    ゴール
    -0.07
    ])==
    -0.07
     ab
    -0.07
     ensemble
    -0.07
    <Scalar
    -0.07
    ガイ
    -0.07
    kek
    -0.06
     diagonal
    -0.06
    geh
    -0.06
    Court
    -0.06
    POSITIVE LOGITS
     perhaps
    0.07
    WARN
    0.07
     në
    0.07
     trữ
    0.07
     Lastly
    0.06
     בעוד
    0.06
    .camel
    0.06
    一座
    0.06
    着他
    0.06
     representing
    0.06
    Activations Density 0.004%

    No Known Activations