© 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. 69309
    Prev
    Next
    INDEX
    Explanations

    to/match

    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
    陌
    -0.07
    _VER
    -0.07
     reloc
    -0.07
    昨
    -0.06
    ingles
    -0.06
    XF
    -0.06
    离职
    -0.06
    Dog
    -0.06
    Professional
    -0.06
     smelling
    -0.06
    POSITIVE LOGITS
     guardian
    0.08
    /fw
    0.07
    citation
    0.07
     matrix
    0.07
    派出所
    0.06
     interpolation
    0.06
    hua
    0.06
     gợi
    0.06
     Coul
    0.06
    	un
    0.06
    Activations Density 0.001%

    No Known Activations