© 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. 69514
    Prev
    Next
    INDEX
    Explanations

    Again

    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
     spear
    -0.08
    (coll
    -0.08
     Medic
    -0.07
    擅
    -0.07
    跻身
    -0.07
    edis
    -0.07
     welded
    -0.07
    ꡑ
    -0.07
     DEFINE
    -0.07
    玼
    -0.06
    POSITIVE LOGITS
    ⽬
    0.07
     graduate
    0.07
     uniqu
    0.07
    حصول
    0.07
    $status
    0.07
     ne
    0.07
     Ezek
    0.07
    ACCEPT
    0.07
    _runner
    0.07
    بقاء
    0.07
    Activations Density 0.010%

    No Known Activations