© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26384
    Prev
    Next
    INDEX
    Explanations

    reshape

    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
    .sky
    -0.07
    ⊊
    -0.07
     Leaders
    -0.07
    烷
    -0.07
     במסגר
    -0.07
    ertest
    -0.06
     spark
    -0.06
    משפחת
    -0.06
     Decompiled
    -0.06
    Ἷ
    -0.06
    POSITIVE LOGITS
    .Font
    0.08
     Ал
    0.07
     Paw
    0.07
     introductory
    0.07
    (UIAlertAction
    0.07
    _author
    0.07
    记忆
    0.06
     cosas
    0.06
     Siber
    0.06
    _Com
    0.06
    Activations Density 0.001%

    No Known Activations