© 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. 69292
    Prev
    Next
    INDEX
    Explanations

    debugging network issues

    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
    ittel
    -0.07
    StartElement
    -0.07
     traps
    -0.07
     khó
    -0.06
    いろ
    -0.06
     человек
    -0.06
     Significant
    -0.06
     الوحيد
    -0.06
    .IsNullOr
    -0.06
    제도
    -0.06
    POSITIVE LOGITS
     celebrates
    0.07
    改變
    0.07
    Purchase
    0.06
    ADDRESS
    0.06
     access
    0.06
    пат
    0.06
    攀登
    0.06
    ambda
    0.06
     cb
    0.06
    PLIED
    0.06
    Activations Density 0.086%

    No Known Activations