© 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. 23-RESID-POST-AA
    11. 129826
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carlson
    -0.08
     nastę
    -0.07
    addTo
    -0.07
     formatted
    -0.07
    缺少
    -0.07
    を持つ
    -0.07
    ække
    -0.07
     tekst
    -0.07
     orden
    -0.07
    كسر
    -0.06
    POSITIVE LOGITS
    責
    0.07
    Ж
    0.07
     Eag
    0.07
     GANG
    0.07
    播报
    0.07
    贴
    0.07
    !,
    0.07
    鹮
    0.07
     случаях
    0.07
    (policy
    0.07
    Activations Density 0.031%

    No Known Activations