Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 45348
    Prev
    Next
    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tôn
    -0.08
    .Alter
    -0.08
    (LL
    -0.07
     tér
    -0.07
     тож
    -0.07
    💊
    -0.07
    ndx
    -0.07
     infix
    -0.07
    瘫
    -0.07
    น
    -0.06
    POSITIVE LOGITS
    specialchars
    0.08
     huyện
    0.07
    라는
    0.07
     passionate
    0.07
    が
    0.07
     "...
    0.07
    性格
    0.07
     Salesforce
    0.07
     fifty
    0.07
    rellas
    0.06
    Activations Density 0.000%

    No Known Activations