© 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. 19-RESID-POST-AA
    11. 2500
    Prev
    Next
    INDEX
    Explanations

    defining constants and macros

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     جدا
    -0.07
    (touch
    -0.07
    _terminal
    -0.07
    _AdjustorThunk
    -0.07
     utter
    -0.07
    [K
    -0.07
    乌克兰
    -0.07
    ,p
    -0.06
    _extend
    -0.06
    杈
    -0.06
    POSITIVE LOGITS
    Calling
    0.07
    ECTOR
    0.07
    чер
    0.07
    перед
    0.07
    ])).
    0.07
     Autos
    0.07
    这场比赛
    0.07
    чем
    0.07
     casos
    0.06
    ?>
↵
↵
    0.06
    Activations Density 0.035%

    No Known Activations