© 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. 75856
    Prev
    Next
    INDEX
    Explanations

    c

    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
     hes
    -0.07
    حافظ
    -0.07
     GPL
    -0.07
     exploit
    -0.07
    就把
    -0.07
     compete
    -0.07
     soundtrack
    -0.07
     Estonia
    -0.07
     Hong
    -0.07
    这个世界
    -0.07
    POSITIVE LOGITS
    ߤ
    0.07
    読
    0.07
     ella
    0.07
    (play
    0.07
     referencia
    0.07
    Photo
    0.06
    Prec
    0.06
     Columbia
    0.06
    铻
    0.06
     �
    0.06
    Activations Density 0.000%

    No Known Activations