© 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 EvalsExportsinterp-engineNEWAPI 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. 60211
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    勘
    -0.08
    implement
    -0.07
    过度
    -0.07
    扩张
    -0.07
    (_
    -0.07
    _errno
    -0.07
    <&
    -0.07
     Reconstruction
    -0.07
    懂得
    -0.07
    仅仅
    -0.07
    POSITIVE LOGITS
    Foo
    0.09
     foo
    0.08
    /foo
    0.08
    عين
    0.08
    foo
    0.08
    �
    0.08
    砚
    0.07
    łę
    0.07
    Greetings
    0.07
     Foo
    0.07
    Activations Density 0.006%

    No Known Activations