© 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. 76856
    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
     late
    -0.08
     chịu
    -0.07
    娛
    -0.07
    多半
    -0.07
     helt
    -0.07
     opera
    -0.07
     mice
    -0.07
    alone
    -0.06
     games
    -0.06
    modation
    -0.06
    POSITIVE LOGITS
     Subscription
    0.09
    плод
    0.08
    Slice
    0.07
    _cluster
    0.07
    _ATTRIB
    0.07
     *&
    0.07
    -string
    0.07
     layouts
    0.07
    пар
    0.07
    ;&
    0.07
    Activations Density 0.120%

    No Known Activations